Dynamic Multi Objective Particle Swarm Optimization Based on a New Environment Change Detection Strategy

Abstract

The dynamic of real-world optimization problems raises new challenges to the traditional particle swarm optimization (PSO). Responding to these challenges, the dynamic optimization has received considerable attention over the past decade. This paper introduces a new dynamic multi-objective optimization based particle swarm optimization (Dynamic-MOPSO).The main idea of this paper is to solve such dynamic problem based on a new environment change detection strategy using the advantage of the particle swarm optimization. In this way, our approach has been developed not just to obtain the optimal solution, but also to have a capability to detect the environment changes. Thereby, Dynamic-MOPSO ensures the balance between the exploration and the exploitation in dynamic research space. Our approach is tested through the most popularized dynamic benchmark's functions to evaluate its performance as a good method.

DPb-MOPSO: A Novel Dynamic Pareto bi-level Multi-Objective Particle Swarm Optimization Algorithm

“…Also, the DC-NSGA-II [24] algorithm presents a self-adaptive penalty function to deal with time-varying constraint problems. Thus, the Dynamic-MOPSO system [2] adapts a dynamic handling strategy to detect changes by controlling the evolution of the objective function over time and re-initialize all solutions with negative changes to maintain diversity.…”

“…Tested Benchmark Function MOO algorithms adapted for DMOOP SPEA2 , Kim M.(2004) [16] DSW1, DSW2, DTF, FDA DMOPs Multiple Single Objective Pareto Sampling (MSOPS), E. J. Hughes (2003) [11] NSGA-II, Deb et al, (2002) [15] Diversity-Based Approaches Modified NSGA-II : (DNSGA-II)-A and (DNSGA-II)-B, Deb et al, (2007) [14] Modified FDA2 and hydro-thermal scheduling problem Dynamic Constrained NSGA-II (DC-NSGA-II), Azzouzet al, (2015) [24] DCTPs test problems Dynamic-MOPSO Aboud et al, (2017) [2] FDA1, DIMP2 and dMOP3 Memory-Based Approaches Steady-state and Generational EA (SGEA) Jiang et al, (2016) [13] five FDA [22], three dMOP [8], six ZJZ [34] and seven UDF [27]. Adaptive Dynamic NSGA-II (A-Dy-NSGA-II), Azzouz et al, (2017) [25] FDA1, FDA2, DMZDT test functions and WYL Dynamic Competitive Cooperative CO-EA (dCOEA), Gohet al, (2009) [8] FDA1, dMOP1, dMOP2 and dMOP3 Change Prediction-Based Approaches Population Prediction Strategy (PPS), Koo et al, (2010) [17] FDA1, FDA4, dMOP1, dMOP2 and F5-F8 Dynamic MOEA with Predicted Re-Initialization (DMOEA/PRI), Zhou et al, (2007) [3] FDA1 and ZJZ Dynamic Queuing MO Optimizer (D-QMOO), Hatzakis and Wallace (2006) [10] FDA1 Parallel Approaches Work of Cámara et al, (2008) [21] FDA1, modified FDA2 and FDA3 Dynamic Multi-objective Optimization EA (DMOEA), Zheng (2007) [33] FDA1, modified FDA2 and FDA3, FDA4 and FDA5 Dynamic Version of Parallel Single Front Genetic Algorithm (PSFGA), Cámara et al, (2007) [20]FDA1 and FDA2…”

“…Different response strategies using explicit actions like the re-initialization or hypermutation of populations is considered for ensuring fast convergence and diversity [1], [26]. PSO-based approaches are very considered for solving DSOP and a few methods are designed to solve DMOPs [2]. Nonetheless, distributed methods using genetic and population-based strategies have been shown to be important for static optimization [7] which has not been treated for handling the DMOPs.…”

“…So far, the state of the art involves a wealth of comparable algorithms to our novel DPb-MOPSO system over two performance metrics [26] namely the Inverted Generational Distance (IGD) and the Hypervolume Difference (HVD). These include the Multi-objective Evolutionary Algorithm Based on Decomposition (MOEAD) [31], the Dual multi-objective particle swarm optimization (dMOPSO) [18], the Dynamic Non-dominated Sorting Genetic Algorithm II (DNSGA-II) [14], the distributed Multi-Objective Particles Swarms Optimization, based on dynamic subdivision of the population using Pareto fronts (pbMOPSO) [7], the Dynamic Multiobjective Particle Swarm Optimization (Dynamic-MOPSO) [2], the dynamic Competitive-cooperative co-evolutionary Algorithm (dCOEA) [8], the Population Prediction Strategy (PPS) [34], the Steady-State and Generational Evolutionary Algorithm (SGEA) [13] and the Multi-Objective Particles Swarms Optimization (MOPSO) [5].…”

A Species Conservation-Based Particle Swarm Optimization with Local Search for Dynamic Optimization Problems

“…e application of PSO to dynamic optimization problems has been widely studied in recent years [5,[16][17][18][19][20]. Similar to other EAs, there are two key facts that must be faced in the application of PSO to dynamic environment: one is the outdated memory, and the other is the loss of diversity [18].…”