Sina Nayeri, Ebrahim Asadi-Gangraj, Saeed Emami,
Volume 29, Issue 1 (IJIEPR 2018)
Abstract
Natural disasters, such as earthquakes, tsunamis, and hurricanes cause enormous harm during each year. To reduce casualties and economic losses in the response phase, rescue units must be allocated and scheduled efficiently, such that it is a key issues in emergency response. In this paper, a multi-objective mix integer nonlinear programming model (MOMINLP) is proposed to minimize sum of weighted completion times of relief operations as first objective function and makespan as second objective with considering time-window for incidents. The rescue units also have different capability and each incident just can be allocated to a rescue unit that has the ability to do it. By assuming the incidents and rescue units as jobs and machine, respectively, the research problem can be formulated as a parallel-machine scheduling problem with unrelated machines. Multi-Choice Goal programming (MCGP) is applied to solve research problem as single objective problem. The experimental results shows the superiority of the proposed approach to allocate and schedule the rescue units in the natural disasters.
Ebrahim Asadi-Gangraj, Fatemeh Bozorgnezhad, Mohammad Mahdi Paydar,
Volume 30, Issue 2 (IJIEPR 2019)
Abstract
In many real scheduling situations, it is necessary to deal with the worker assignment and job scheduling together. However, in traditional scheduling problems, only the machine is assumed to be a constraint and there isn’t any constraint about workers. This assumption could be due to the lower cost of workers compared to machines or the complexity of workers' assignment problems. This research proposes a flexible flow shop scheduling problem with two simultaneous issues: finding the best worker assignment, and solving the corresponding scheduling problem. We present a mathematical model that extends flexible flow shop scheduling problem to admit the worker assignment. Due to the NP-hardness of the research problem, two approximation approaches based on particle swarm optimization, named PSO and SPSO, are applied to minimize the makespan. The experimental results show that the proposed algorithms can efficiently minimize the makespan but the SPSO generates better solutions especially for large-size problems.
