Dynamic Multi-objective Optimization Using Evolutionary Algorithms: A Survey

Azzouz, Radhia; Bechikh, Slim; Saïd, Lamjed Ben

doi:10.1007/978-3-319-42978-6_2

Cited by 94 publications

(51 citation statements)

References 69 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are several types of dynamics in the literature of multi-objective optimisation. Frequency, severity and predictability are the prominent categories among them (Azzouz et al, 2017a). Farina et al (2004) described four types of DMOPs according to the changes affecting the optimal Pareto Front (PF) and Pareto Set (PS).…”

Section: Defining the Dynamics Of The Dmopmentioning

confidence: 99%

“…known weights, unknown weights and decision support scenario) where authors showed one or both conversions are impossible, infeasible or undesirable. In addition, as far as dynamic multi-objective optimisation is concerned, very few studies have been conducted in this area due to the lack of testbeds (Azzouz et al, 2017a). In this research, we targeted to fill up this gap by proposing a dynamic multi-objective testbed (i.e.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Dynamic multi-objective optimisation using deep reinforcement learning: benchmark, algorithm and an application to identify vulnerable zones based on water quality

Hasan

Lwin

Imani

et al. 2019

Engineering Applications of Artificial Intelligence

View full text Add to dashboard Cite

Dynamic multi-objective optimisation problem (DMOP) has brought a great challenge to the reinforcement learning (RL) research area due to its dynamic nature such as objective functions, constraints and problem parameters that may change over time. This study aims to identify the lacking in the existing benchmarks for multi-objective optimisation for the dynamic environment in the RL settings. Hence, a dynamic multi-objective testbed has been created which is a modified version of the conventional deep-sea treasure (DST) hunt testbed. This modified testbed fulfils the changing aspects of the dynamic environment in terms of the characteristics where the changes occur based on time. To the authors' knowledge, this is the first dynamic multi-objective testbed for RL research, especially for deep reinforcement learning. In addition to that, a generic algorithm is proposed to solve the multi-objective optimisation problem in a dynamic constrained environment that maintains equilibrium by mapping different objectives simultaneously to provide the most compromised solution that closed to the true Pareto front (PF). As a proof of concept, the developed algorithm has been implemented to build an expert system for a real-world scenario using Markov decision process to identify the vulnerable zones based on water quality resilience in São Paulo, Brazil. The outcome of the implementation reveals that the proposed parity-Q deep Q network (PQDQN) algorithm is an efficient way to optimise the decision in a dynamic environment. Moreover, the result shows PQDQN algorithm performs better compared to the other state-of-the-art solutions both in the simulated and the real-world scenario.

show abstract

Section: Defining the Dynamics Of The Dmopmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Dynamic multi-objective optimisation using deep reinforcement learning: benchmark, algorithm and an application to identify vulnerable zones based on water quality

Hasan

Lwin

Imani

et al. 2019

Engineering Applications of Artificial Intelligence

View full text Add to dashboard Cite

show abstract

“…Different change response strategies with different approaches have been previously proposed. In Azzouz, Bechikh, and Said (2017a), these approaches are classified considering what is the response strategy based on: diversity by population replacement, change prediction, use of external memory, the application of parallel EAs or dividing a DMOP into multiple non-dynamic MOPs.…”

Section: Evolutionary Algorithms In Dmopsmentioning

confidence: 99%

Application of Population Evolvability in a Hyper-Heuristic for Dynamic Multi-Objective Optimization

Macias-Escobar

Cruz-Reyes

Dorronsoro

et al. 2019

Technological and Economic Development of Economy

View full text Add to dashboard Cite

It is important to know the properties of an optimization problem and the difficulty an algorithm faces to solve it. Population evolvability obtains information related to both elements by analysing the probability of an algorithm to improve current solutions and the degree of those improvements. DPEM_HH is a dynamic multi-objective hyper-heuristic that uses low-level heuristic (LLH) selection methods that apply population evolvability. DPEM_HH uses dynamic multiobjective evolutionary algorithms (DMOEAs) as LLHs to solve dynamic multi-objective optimization problems (DMOPs). Population evolvability is incorporated in DPEM_HH by calculating it on each candidate DMOEA for a set of sampled generations after a change is detected, using those values to select which LLH will be applied. DPEM_HH is tested on multiple DMOPs with dynamic properties that provide several challenges. Experimental results show that DPEM_HH with a greedy LLH selection method that uses average population evolvability values can produce solutions closer to the Pareto optimal front with equal to or better diversity than previously proposed heuristics. This shows the effectiveness and feasibility of the application of population evolvability on hyperheuristics to solve dynamic optimization problems.

show abstract

“…Dynamic multiobjective optimization problem (DMOP) can be defined as the problem of determining the decision variables, which satisfies the set of constraints and optimizes the set of objective functions that change during the optimization process. The mathematical formulation of minimization problem of DMOP can be described as follows:

\begin{matrix} lefttrue \\ Min F (x, D, P) = \{f_{1} (x, D P) f_{2} (x, D, P), ⋯, f_{Q} (x, D, P)\} \\ Subject to : G (x) \geq 0 \\ H (x) = 0, \end{matrix}

where x = ( x 1 , x 2 , …, x n ) is the decision variables vector; F is the set of objectives to be minimized.…”

Section: Prerequisite Mathematics On Dmopmentioning

confidence: 99%

“…Dynamic multiobjective optimization problem (DMOP) 39,40 can be defined as the problem of determining the decision variables, which satisfies the set of constraints and optimizes the set of objective functions that change during the optimization process. The mathematical formulation of minimization problem of DMOP can be described as follows:…”

Section: Prerequisite Mathematics On Dmopmentioning

confidence: 99%

A novel PSO algorithm for dynamic wireless sensor network multiobjective optimization problem

El-Shorbagy

Elhoseny

Hassanien

et al. 2018

Trans Emerging Tel Tech

View full text Add to dashboard Cite

All real‐life multiobjective optimization problems (MOPs) are considered dynamic. It is occurring due to fluctuations in environmental or the global market instabilities that lead to the quick fluctuations of prices. Wireless sensor network optimization problem, by nature, is considered one of the dynamic MOP (DMOP) and needs to be solved by a special method to save time and effort. Thus, this paper proposed a novel particle swarm optimization (PSO) for dynamic wireless sensor network MOP to accelerate data transfer in networks and reduce energy losses. Generally, in DMOPs, the optimization period is broken into several equal subperiods. In each subperiod, there is a dynamic parameter that changes. In the proposed approach, PSO is used to handle DMOPs without any changing of its structure and has fast convergence properties. However, a new mechanism to choose the personal and global preferred particles is introduced, which based on the distance between the nondominated solutions obtained so far and the particles positions by using Euclidean metric. In addition, two types of archives are used to maintain the nondominated solutions. The first one is used to store the nondominated solutions obtained by each particle, whereas the second type is used to store the nondominated solutions achieved by all particles. The novel methodology performance is proved by applying it on three benchmark problems that were chosen from the literature and one design problem from the engineering domain. The simulation results mentioned that the proposed algorithm is active and efficacious in solving DMOPs.

show abstract

Dynamic Multi-objective Optimization Using Evolutionary Algorithms: A Survey

Cited by 94 publications

References 69 publications

Dynamic multi-objective optimisation using deep reinforcement learning: benchmark, algorithm and an application to identify vulnerable zones based on water quality

Dynamic multi-objective optimisation using deep reinforcement learning: benchmark, algorithm and an application to identify vulnerable zones based on water quality

Application of Population Evolvability in a Hyper-Heuristic for Dynamic Multi-Objective Optimization

A novel PSO algorithm for dynamic wireless sensor network multiobjective optimization problem

Contact Info

Product

Resources

About