Development, application, and comparison of hybrid meta-heuristics for urban land-use allocation optimization: Tabu search, genetic, GRASP, and simulated annealing algorithms

摘要

Land-use optimization problem (LUOP) that seeks to allocate different land types to land units involves various dimensions and deals with numerous conflicting objectives and a large set of data and variables. Single meta heuristics are broadly developed and applied for solving LUOP. Despite the acceptable solutions derived from these algorithms, researchers in both academic and practical areas face the interesting question: can we develop an algorithm with better efficiency and solution quality? In the literature of operation research, hybridization, a combination of meta-heuristics, was introduced as a way of generating better algorithms. Therefore, this paper aims at developing novel algorithms through hybridizing Tabu search (TS), genetic algorithm (GA), GRASP, and simulated annealing (SA) and examining their quality and efficiency in practice. Accordingly, low-level teamwork GRASP-GA-TS (LLTGRGATS), high-level relay Greedy-GA-TS, and high-level teamwork SA were developed. Firstly, these algorithms were applied for solving small- and large-size single-row facility layout problem to evaluate their performance and functionality and to select the satisfactory algorithm in comparison with the other developed hybrids. Secondly, the selected algorithm, LLTGRGATS, and SVNS, a recent hybrid algorithm proposed for solving LUOP, were performed on a study area to solve a LUOP with two constraints and seven nonlinear objective functions. The outputs showed that the quality and efficiency of LLTGRGATS were slightly better than those of SVNS and it can be considered as a favorable tool for land-use planning process. (C) 2016 Elsevier Ltd. All rights reserved.