@inproceedings { , title = {Iteration-related various learning particle swarm optimization for quay crane scheduling problem}, abstract = {Quay crane scheduling is critical in reducing operation costs at container terminals. Designing a schedule to handling containers in an efficient order can be difficult. For this problem which is proved NP-hard, heuristic algorithms are effective to obtain preferable solutions within limited computational time. When solving discrete optimization problems, particles are very susceptible to local optimum in Standard Particle Swarm Optimization (SPSO). To overcome this shortage, this paper proposes an iteration-related various learning particle swarm optimization (IVLPSO). This algorithm employs effective mechanisms devised to obtain satisfactory quay crane operating schedule efficiently. Superior solutions can save up to 5 h for handling a batch of containers, thus significantly reduces costs for terminals. Numerical studies show that the proposed algorithm outperforms state-of-the-art existing algorithms. A series of experimental results demonstrate that IVLPSO performs quite well on obtaining satisfactory Pareto set with quick convergence.}, conference = {The 13th International Conference on Bio-inspired Computing: Theories and Applications}, doi = {10.1007/978-981-13-2829-9\_19}, isbn = {9789811328282}, pages = {201-212}, publicationstatus = {Published}, publisher = {Springer Publishing Company}, url = {https://nottingham-repository.worktribe.com/output/1283778}, year = {2018}, author = {Yu, Mingzhu and Cong, Xuwen Cong and Niu, Ben and Qu, Rong} }