Enhanced NSGA-II with evolving directions prediction for interval multi-objective optimization

Sun, Xiaoyan; Zhao, Lin; Zhang, Pengfei; Bao, Lin; Yang, Chao

doi:10.1016/j.swevo.2019.05.009

Cited by 26 publications

(7 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…5 that a high demand does not necessarily lead to a high risk (high occupancy). For the studied 31 days, we notice that days 1,5,6,7,14,15,20,21,23,26,28,31 as reected in Fig. 5 have occupancies larger than the average occupancy.…”

Section: Experimental Study a Trafc Scenariomentioning

confidence: 85%

See 1 more Smart Citation

A Multiobjective Optimization Approach for Air Traffic Flow Management for Airspace Safety Enhancement

Cai

Ang

Alam

2022

2022 IEEE Congress on Evolutionary Computation (CEC)

View full text Add to dashboard Cite

This work aims to enhance the safety of air trafc in a procedural airspace by air trafc ow management (ATFM) without compromizing air trafc demand. In civil aviation, collision risk is an important indicator for air trafc safety assessment. In this work, we propose a generic ATFM framework based on multiobjective optimization for reducing lateral collision risk of the trafc in a given procedural airspace. The proposed framework aims to optimize the ight level assignment for a given set of ight plans such that the lateral collision risk can be reduced. To achieve this goal, we formulate an optimization problem containing two partially conicting objective functions. We then adopt three well-known evolutionary algorithms, i.e., MODPSO, NSGA-II, and MOEA/D to solve the optimization problem. We specially design some of the operators of those algorithms to make them suitable for the optimization problem. We merge the solutions yielded by those three algorithms and lter out the nal Pareto solutions. We carry out a case study on the procedural airspace of Singapore ight information region (FIR) with respect to twelve daily trafc data selected from the real trafc data for December 2019. Experiment results demonstrates that the lateral occupancy which is the key contributor to lateral risk can be reduced by 10.65% to 93.05% at a strategic planning level. This research contribute to strategic ight planning by assigning ight levels that may reduce the risk of collision in procedural airspace.

show abstract

Section: Experimental Study a Trafc Scenariomentioning

confidence: 85%

“…Note that the formulated optimization problem is a non convex problem. In order to solve it, we adopt three well known evolutionary algorithms named MODPSO [14], NSGA II [15][16][17] and MOEA/D [18,19]. For each algorithm, we specially design its key operators to make them suitable for the optimization problem.…”

Section: Introductionmentioning

confidence: 99%

A Multiobjective Optimization Approach for Air Traffic Flow Management for Airspace Safety Enhancement

Cai

Ang

Alam

2022

2022 IEEE Congress on Evolutionary Computation (CEC)

View full text Add to dashboard Cite

show abstract

“…Many MOMHAs also introduced several frameworks, motivated by this concept, that uses the Pareto-dominance principle to rate the proximity of optimal PF solution. For instance, Deb et al rated the optimal solution using NSGA-II non-dominatedranking mechanism [43,44]. Multi-objective Seagull Optimization Algorithm [45], MOEAs [46], NSGA-III [47], bare-bones multi-objective particle swarm optimization [48], MOPSO [49], multi-swarm cooperative multiobjective particle swarm optimizer [50], MOWCA [51], incremental learning hybridized with adaptive differential evolution [52], MOSOS [53], and cooperative coevolutionary optimization [54] are among the well-known Pareto-based MOMHAs in the literary works.…”

Section: B Related Workmentioning

confidence: 99%

MOSMA: Multi-Objective Slime Mould Algorithm Based on Elitist Non-Dominated Sorting

Premkumar¹,

Jangir²,

Sowmya

et al. 2021

IEEE Access

171

View full text Add to dashboard Cite

This paper proposes a multi-objective Slime Mould Algorithm (MOSMA), a multi-objective variant of the recently-developed Slime Mould Algorithm (SMA) for handling the multi-objective optimization problems in industries. Recently, for handling optimization problems, several meta-heuristic and evolutionary optimization techniques have been suggested for the optimization community. These methods tend to suffer from low-quality solutions when evaluating multi-objective optimization (MOO) problems than addressing the objective functions of identifying Pareto optimal solutions' accurate estimation and increasing the distribution throughout all objectives. The SMA method follows the logic gained from the oscillation behaviors of slime mould in the laboratory experiments. The SMA algorithm shows a powerful performance compared to other well-established methods, and it is designed by incorporating the optimal food path using the positive-negative feedback system. The proposed MOSMA algorithm employs the same underlying SMA mechanisms for convergence combined with an elitist non-dominated sorting approach to estimate Pareto optimal solutions. As a posteriori method, the multi-objective formulation is maintained in the MOSMA, and a crowding distance operator is utilized to ensure increasing the coverage of optimal solutions across all objectives. To verify and validate the performance of MOSMA, 41 different case studies, including unconstrained, constrained, and real-world engineering design problems are considered. The performance of the MOSMA is compared with Multiobjective Symbiotic-Organism Search (MOSOS), Multi-objective Evolutionary Algorithm Based on Decomposition (MOEA/D), and Multiobjective Water-Cycle Algorithm (MOWCA) in terms of different performance metrics, such as Generational Distance (GD), Inverted Generational Distance (IGD), Maximum Spread (MS), Spacing, and Run-time. The simulation results demonstrated the superiority of the proposed algorithm in realizing high-quality solutions to all multi-objective problems, including linear, nonlinear, continuous, and discrete Pareto optimal front. The results indicate the effectiveness of the proposed algorithm in solving complicated multi-objective problems. This research will be backed up with extra online

show abstract

“…Consequently, most of literatures have been reported according to this idea to exploit the predictability of dynamic environments. For example, Zhang et al put forward novel prediction strategies [9], which combines a new prediction-based reaction mechanism and a popular regularity model-based multi-objective estimation of distribution algorithm; Rong et al proposed a multi-model [40]; and so on. These kind of algorithms have solved the DMOPs to some extend, but their effectiveness is still questionable if the change in the environment is, as DMOPs with different the challenge characteristic lead to mostly happens or hardly predictable.…”

Section: B Related Workmentioning

confidence: 99%

A Novel Prediction Strategy Based on Change Degree of Decision Variables for Dynamic Multi-Objective Optimization

Xing

Liu

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Effectively balancing the convergence and diversity in dynamic environments is a challenging task. In order to handle the issue, this paper proposes a novel prediction strategy based on change degree of decision variables for dynamic multi-objective optimization (CDDV), which has the ability to detect the change degree in the decision space and design the different prediction strategy to make the population adapt to the new environment. The proposed method can adaptively increase population diversity according to the analysis of change degree, when an environmental change is detected. In order to study the efficacy and usefulness of the novel change degree on evolutionary algorithms, a range of dynamic multi-objective benchmark problems are selected to evaluate the performance of the proposed algorithm. The results demonstrate the effectiveness of proposed algorithm in compared with four other state-of-the-art methods. INDEX TERMS Dynamic multi-objective optimization, evolutionary algorithms, change degree, diversity.

show abstract

Enhanced NSGA-II with evolving directions prediction for interval multi-objective optimization

Cited by 26 publications

References 32 publications

A Multiobjective Optimization Approach for Air Traffic Flow Management for Airspace Safety Enhancement

A Multiobjective Optimization Approach for Air Traffic Flow Management for Airspace Safety Enhancement

MOSMA: Multi-Objective Slime Mould Algorithm Based on Elitist Non-Dominated Sorting

A Novel Prediction Strategy Based on Change Degree of Decision Variables for Dynamic Multi-Objective Optimization

Contact Info

Product

Resources

About