Construction site layout planning using multi-objective artificial bee colony algorithm with Levy flights
Introduction
Construction site layout planning (CSLP) has been recognized as a critical step in construction planning [1]. The basic function of this process is to find the best arrangement of the temporary facilities according to multiple objectives that may conflict with each other and subjected to logical and resources constraints. Minimizing the cost associated with the interaction between facilities and minimizing safety and environmental hazards are most popular conflicting planning objectives that have been studied in recent studies [2], [3], [4]. In most of the previous work the CSLP problem is considered a static layout problem assuming that all temporary facilities are assembled at the beginning and kept at their initial locations until the completion of the project [5], [6], [7], [8]. However in the real situation, the need of temporary facilities varies during different construction phases of the projects and basically depends on activity schedules. Zouein and Tommelein [9] emphasized the importance of considering the interdependence between activity scheduling and site layout. Because of its significant effects on the reliability of the results, most recent studies consider the dynamic search scheme for solving the CSLP problem [2], [3].
Construction site layout planning is considered as ‘NP-hard’ problem [8] for its complexity. The recent meta-heuristic algorithms based on swarm intelligence have demonstrated their power in finding the solution of such type of optimization problems [10]. This has encouraged researchers to employ these modern meta-heuristic algorithms to determine the solution of their proposed CSLP models. Ning et al. in their work [3] proposed a method to solve the dynamic multi-objective CSLP problem using max–min Ant system (MMAS) which is one of the versions of standard ant colony optimization (ACO) algorithms. Lien and Cheng [8] proposed a hybrid swarm intelligence based particle-bee algorithm for construction site layout optimization under single objective function to locate facilities in predetermined locations. Li and Love [5] presented an investigation of applying the Genetic Algorithm to attain the optimal solution for single objective CSLP problem to accommodate facilities of un-equal area in predetermined locations. Zang and Wang [11] proposed a particle swarm optimization (PSO) based methodology. They modeled the CSLP problem to optimize static layout under single objective function to accommodate facilities of un-equal area in predetermined locations. Another study related to particle swarm optimization (PSO) was developed by Jiuping Xu and Zongmin Li [2]. Their approach uses multi-objective particle swarm optimization (MOPSO) algorithm. The approach is applied to solve the multi objective dynamic CSLP problem. Osman et al. proposed a hybrid cad-based algorithm using genetic algorithm (GA) in order to optimize the assignment of un-equal area facilities to any unoccupied space at a construction site [12].
The artificial bee colony (ABC) algorithm is one of the most recent swarm intelligence based algorithms introduced by Dervis Karaboga which mimics the foraging behavior of honey bees [13]. In this study a multi objective artificial bee colony (MOABC) algorithm is used to obtain the solution of the CSLP problem. The standard MOABC algorithm is enhanced with Levy flights type of random walks for finding new food sources which is conducted by employed bees. The objective of the study is to optimize the dynamic layout problem under two objective functions of minimizing the safety hazards/environmental concerns and the total handling cost of interaction flows between facilities. The model regards the CSLP problem as a non-linear layout problem with un-equal area facilities that can be aligned horizontally or vertically. Furthermore the model takes into account the presence of obstructions for determining travel distances.
The remainder of the paper is organized as follows. In Section 2, the CSLP model is described; in Section 3 the multi-objective ABC algorithm with Levy flights is explained. Section 4 presents the design examples. The conclusion is presented in Section 5.
Section snippets
Modeling of construction site layout problem model
Construction site layout planning layout model is designed to arrange temporary facilities required at various time intervals (phases) of construction project under set of constraints while achieving multi objective functions. Generally in multi-objective optimization problems pareto optimal solutions are determined so that decision makers can choose their preferred plan among these pareto optimal solutions [2]. The efficiency of CSLP model will be significantly affected by its precision in
Artificial bee colony (ABC) algorithm
Introduced by Dervis Karaboga in 2005, ABC algorithm simulated the foraging behavior of a bee colony. Bees aim to maximize the nectar amount unloaded to the food stores in the hive. In the ABC algorithm a honey bee swarm is classified to three categories: employed bees, onlooker bees, and scout bees. Half of the colony bees are employed bees and each food source is exploited by only one employed bee that carries information about this particular food source and share information with other bees
Design examples
The multi-objective optimization algorithm developed is applied to determine the optimum site layout problems of two construction projects. The first one is a residential building construction project located in the city of Beijing, China. This example is taken from [3] where optimum site layout problem is solved by using ant colony algorithm. The purpose of considering the same example is to provide an environment for comparing the performance of two algorithms. The second example is the
Conclusions
In this article, a multi objective decision making model for dynamic construction site layout planning problem is proposed which makes use of novel MOABC via Levy flights algorithm. The performance of the proposed CSLP model based on multi objective artificial bee colony via Levy flights (MOABC via Levy flights) is compared with Basic-MOABC model, max–min Ant system (MMAS) model, and the original construction site layout of the studied problem. Results show that MOABC via Levy flights performs
References (26)
- et al.
A decision-making system for construction site layout planning
Automation in Construction
(2011) - et al.
Dynamic construction site layout planning using max–min ant system
Automation in Construction
(2010) - et al.
Automated multi-objective optimization system for airport site layouts
Automation in Construction
(2011) - et al.
Genetic search for solving construction site-level unequal-area construction site layout problems
Automation in Construction
(2000) - et al.
Site pre-cast yard layout arrangement through genetic algorithms
Automation in Construction
(2002) - et al.
A hybrid CAD-based construction site layout planning system using genetic algorithms
Automation in Construction
(2003) - et al.
Automating dynamic layout construction, automation and robotics in construction
ASCE
(1994) - et al.
A comparative study of artificial bee colony algorithm
Applied Mathematics and Computation
(2009) - et al.
A modified artificial bee colony (abc) algorithm for constrained optimization problems
Applied Soft Computing
(2011) An efficient constraint handling method for genetic algorithms
Computer Methods in Applied Mechanics and Engineering
(2000)
Cuckoo search via Levy flights
Proceedings of World Congress on Nature & Biologically Inspired Computing (NaBIC2009India)
Multi-objective dynamic construction site layout planning in fuzzy random environment
Automation in Construction
Construction site-layout using annealed neural network
Journal of Computing in Civil Engineering
Cited by (119)
Lévy Arithmetic Algorithm: An enhanced metaheuristic algorithm and its application to engineering optimization
2024, Expert Systems with ApplicationsAutomatic tower crane layout planning system for high-rise building construction using generative adversarial network
2023, Advanced Engineering InformaticsEvolving Marine Predators Algorithm by dynamic foraging strategy for real-world engineering optimization problems
2023, Engineering Applications of Artificial IntelligenceHybridization of reinforcement learning and agent-based modeling to optimize construction planning and scheduling
2022, Automation in Construction