dynamicmulti -objectiveoptimizationproblems (DMOPs) are prevalent in the real world, where the challenge in solving DMOPs is how to track the time -varying Pareto-optimal front (PF) and Pareto-optimal set (PS) quic...
详细信息
dynamicmulti -objectiveoptimizationproblems (DMOPs) are prevalent in the real world, where the challenge in solving DMOPs is how to track the time -varying Pareto-optimal front (PF) and Pareto-optimal set (PS) quickly and accurately. However, balancing convergence and diversity is challenging as a single strategy can only address a particular type of DMOP. To solve this issue, a dynamicmulti -objectiveoptimization evolutionary algorithm with adaptive boosting (AB-DMOEA) is proposed in this paper. In the AB-DMOEA, an adaptive boosting response mechanism will increase the weights of high -performing strategies, including those based on prediction, memory, and diversity, which have been improved and integrated into the mechanism to tackle various problems. Additionally, the dominated solutions reinforcement strategy optimizes the population to ensure the effective operation of the above mechanism. In static optimization, the static optimization boosting mechanism selects the appropriate static multi -objective optimizer for the current problem. AB-DMOEA is compared with the other seven state-of-the-art DMOEAs on 35 benchmark DMOPs. The comprehensive experimental results demonstrate that the overall performance of the AB-DMOEA is superior or comparable to that of the compared algorithms. The proposed AB-DMOEA is also successfully applied to the smart greenhouses problem.
Network Function Visualization (NFV) is a technology that promises to provide greater flexibility and dynamism than the traditional, conventional networks with middlebox hardware. These benefits bring with them the ch...
详细信息
ISBN:
(纸本)9781450394291
Network Function Visualization (NFV) is a technology that promises to provide greater flexibility and dynamism than the traditional, conventional networks with middlebox hardware. These benefits bring with them the challenge of calculating routes and locating multiple virtual network functions (VNF) in the network nodes to respond to complex traffic requirements. This problem is called virtual network function chaining placement (VNF Chaining Placement, VNF-CP) which has been discussed in the context of static optimization for both static and dynamic traffic. Given the dynamics and complexity of the VNF-CP problem, this paper proposes a framework that combines dynamicmulti-objectiveoptimization (DMO) and multi-criteria decision making (MCDM) in the process of solution deployment. The framework makes five actions in each operational cycle: it receives and analyses network traffic, determines the most relevant objective functions based on the traffic state, recomputes the non-dominated solutions set using a DMO algorithm, and finally selects a solution to deploy using an MCDM algorithm. In order to determine the effectiveness of the framework, the performance of dynamicmulti-objective evolutionary algorithms (DMOEA) has been studied, state-of-the-art competitive (DNSGAII-A and DNSGAII-B) compared to traditional MOEAs, non-dynamic (NSGAIII, MOEAD, and REVEA) considering TOPSIS as MCDM scheme. The results of numeric simulations in the test instances show that the dynamic DMOEAs resolve the VNF-CP problem competitively and with promising results compared to traditional MOEAs.
Solving dynamic multi-objective optimization problem (DMOP) requires optimizing multiple conflicting objectives simultaneously. When a dynamic is detected in the changing environment, most of existing prediction-based...
详细信息
ISBN:
(数字)9781728169293
ISBN:
(纸本)9781728169293
Solving dynamic multi-objective optimization problem (DMOP) requires optimizing multiple conflicting objectives simultaneously. When a dynamic is detected in the changing environment, most of existing prediction-based strategies predict the trajectory of changing Pareto-optimal solutions (POS), based on the historical solutions obtained in the solution space. In this paper, we present a new prediction method to track the moving optima for solving DMOP. In contrast to existing approaches, we propose to build the prediction model in the objective space. As the evaluation for solving a DMOP is based on the Pareto-optimal front (POF), to predict directly in the objective space could provide more useful information than the prediction in the solution space. In particular, to efficiently capture the complex relationships among POFs found along the evolutionary search, here we build a prediction model in Reproducing Kernel Hilbert Space, which holds a closed-form solution. To evaluate the performance of the proposed method, empirical studies have been conducted by comparing against three state-of-the-art prediction-based strategies on fourteen commonly used DMOP benchmarks. The results obtained by using different optimization solvers confirmed the superiority of the proposed method for solving DMOP in terms of both solution quality and time efficiency.
Many real-world multi-objectiveoptimizationproblems are subject to environmental changes over time, resulting in changing Pareto-optima. Wide studies on solving dynamic multi-objective optimization problems have so ...
详细信息
Many real-world multi-objectiveoptimizationproblems are subject to environmental changes over time, resulting in changing Pareto-optima. Wide studies on solving dynamic multi-objective optimization problems have so far concentrated on tracking moving Pareto-optima as soon as possible. In practice, however, a new solution every time the environmental change may be different from the previous optima, causing the expensive switching-cost. To this end, dynamic robust multi-objectiveoptimization method is developed to find robust Pareto-optima over time whose performance is acceptable for the current and subsequently changed environments. With the purpose of measuring the robustness of a candidate, its fitness values in the subsequent environments are estimated by ensemble prediction methods constructed by moving average(MA), autoregressive(AR), and single exponential smoothing(SES). MA-, SES- and AR-based sub-prediction models are synthesized by the weight sum. The weights can be the pre-set constant or the binary/real number adjusted in terms of the prediction error. To examine the performance of the developed algorithm, the proposed prediction strategies are compared with three single prediction methods for 11 dynamic benchmark functions. The experimental results indicate that ensemble prediction methods have the better robustness than the single prediction models and can effectively tackle dynamic robust multi-objectiveoptimizationproblems.
暂无评论