Physical programming for preference driven evolutionary multi-objective optimization

Preference articulation in multi-objective optimization could be used to improve the pertinency of solutions in an approximated Pareto front. That is, computing the most interesting solutions from the designer's point of view in order to facilitate the Pareto front analysis and the selection of a design alternative. This articulation can be achieved in an a priori, progressive, or a posteriori manner. If it is used within an a priori frame, it could focus the optimization process toward the most promising areas of the Pareto front, saving computational resources and assuring a useful Pareto front approximation for the designer. In this work, a physical programming approach embedded in an evolutionary multi-objective optimization is presented as a tool for preference inclusion. The results presented and the algorithm developed validate the proposal as a potential tool for engineering design by means of evolutionary multi-objective optimization.     

A multi-objective artificial physics optimization algorithm based on ranks of individuals

This paper proposes a multi-objective artificial physics optimization algorithm based on individuals’ ranks. Using a Pareto sorting based technique and incorporating the concept of neighborhood crowding degree, evolutionary individuals in the search space are evaluated at first. Then each individual is assigned a unique serial number in terms of its performance, which affects the mass of the individual. Thereby, the population evolves towards the direction of the Pareto-optimal front. Synchronously, the presented approach has good diversity, such that the population is spread evenly on the Pareto front. Results of simulation on a number of difficult test problems show that the proposed algorithm, with less evolutionary generations, is able to find a better spread of solutions and better convergence near the true Pareto-optimal front compared to classical multi-objective evolutionary algorithms (NSGA, SPEA, MOPSO) and to simple multi-objective artificial physics optimization algorithm.     

基于幂变换的多目标进化算法MOEA?D权重设计方法

在多目标最优化问题中,如何求解一组均匀散布在前沿界面上的有效解具有重要意义.MOEA?D是最近出现的一种杰出的多目标进化算法,当前沿界面的形状是某种已知的类型时,MOEA?D使用高级分解的方法容易求出均匀散布在前沿界面上的有效解.然而,多目标优化问题的前沿界面的形状通常是未知的.为了使MOEA?D能求出一般多目标优化问题的均匀散布的有效解,利用幂函数对目标进行数学变换,使变换后的多目标优化问题的前沿界面在算法的进化过程中逐渐接近希望得到的形状,提出了一种求解一般的多目标优化问题的MOEA?D算法的权重设计方法,并且讨论了经过数学变换后前沿界面的保距性问题.采用建议的权重设计方法,MOEA?D更容易求出一般的多目标优化问题均匀散布的有效解.数值结果验证了算法的有效性.     

Evolutionary multi-objective optimisation with preferences for multivariable PI controller tuning

Multi-objective optimisation design procedures have shown to be a valuable tool for control engineers. They enable the designer having a close embedment of the tuning process for a wide variety of applications. In such procedures, evolutionary multi-objective optimisation has been extensively used for PI and PID controller tuning; one reason for this is due to their flexibility to include mechanisms in order to enhance convergence and diversity. Although its usability, when dealing with multi-variable processes, the resulting Pareto front approximation might not be useful, due to the number of design objectives stated. That is, a vast region of the objective space might be impractical or useless a priori, due to the strong degradation in some of the design objectives. In this paper preference handling techniques are incorporated into the optimisation process, seeking to improve the pertinency of the approximated Pareto front for multi-variable PI controller tuning. That is, the inclusion of preferences into the optimisation process, in order to seek actively for a pertinent Pareto front approximation. With such approach, it is possible to tune a multi-variable PI controller, fulfilling several design objectives, using previous knowledge from the designer on the expected trade-off performance. This is validated with a well-known benchmark example in multi-variable control. Control tests show the usefulness of the proposed approach when compared with other tuning techniques.     

Optimal driving during electric vehicle acceleration using evolutionary algorithms

Due to the limited amount of stored battery energy it is necessary to optimally accelerate electric vehicles (EVs), especially in urban driving cycles. Moreover, a quick speed change is also important to minimize the trip time. Conversely, for comfortable driving, the jerk experienced during speed changing must be minimum. This study focuses on finding a comfortable driving strategy for EVs during speed changes by solving a multi-objective optimization problem (MOOP) with various conflicting objectives. Variants of two different competing evolutionary algorithms (EAs), NSGA-II (a non-dominated sorting multi-objective genetic algorithm) and SPEA 2 (strength Pareto evolutionary algorithm), are adopted to solve the problem. The design parameters include the acceleration value(s) with the associated duration(s) and the controller gains. The Pareto-optimal front is obtained by solving the corresponding MOOP. Suitable multi-criterion decision-making techniques are employed to select a preferred solution for practical implementation. After an extensive analysis of EA performance and keeping online implementation in mind, it was observed that NSGA-II with the crowding distance approach was the most suitable. A recently proposed innovization procedure was used to reveal salient properties associated with the obtained trade-off solutions. These solutions were analyzed to study the effectiveness of various parameters influencing comfortable driving.     

基于决策者偏好区域的多目标粒子群算法研究*

多目标优化问题中,决策者往往只对目标空间的某一区域感兴趣,因此需要在这一特定的区域能够得到比较稠密的Pareto解,但传统的方法却找出全部的Pareto前沿,决策效率不高。针对该问题,给出了基于决策者偏好区域的多目标粒子群优化算法。它只求出与决策者偏好区域相关的部分Pareto最优集,从而减少了进化代数,加快收敛速度,有利于决策者进行更有效的决策。算法把解与偏好区域的距离作为影响引导者选择和剪枝策略的一个因素,运用格栅方法实现解在Pareto边界分布的均匀性。仿真结果表明该算法是有效的。     

Nonlinear channel equalizer design using directional evolutionary multi-objective optimization

In this paper, a new equalizer learning scheme is introduced based on the algorithm of the directional evolutionary multi-objective optimization (EMOO). Whilst nonlinear channel equalizers such as the radial basis function (RBF) equalizers have been widely studied to combat the linear and nonlinear distortions in the modern communication systems, most of them do not take into account the equalizers’ generalization capabilities. In this paper, equalizers are designed aiming at improving their generalization capabilities. It is proposed that this objective can be achieved by treating the equalizer design problem as a multi-objective optimization (MOO) problem, with each objective based on one of several training sets, followed by deriving equalizers with good capabilities of recovering the signals for all the training sets. Conventional EMOO which is widely applied in the MOO problems suffers from disadvantages such as slow convergence speed. Directional EMOO improves the computational efficiency of the conventional EMOO by explicitly making use of the directional information. The new equalizer learning scheme based on the directional EMOO is applied to the RBF equalizer design. Computer simulation demonstrates that the new scheme can be used to derive RBF equalizers with good generalization capabilities, i.e., good performance on predicting the unseen samples.     

Convergence of multi-objective evolutionary algorithms to a uniformly distributed representation of the Pareto front

In evolutionary multi-objective optimization (EMO), the convergence to the Pareto set of a multi-objective optimization problem (MOP) and the diversity of the final approximation of the Pareto front are two important issues. In the existing definitions and analyses of convergence in multi-objective evolutionary algorithms (MOEAs), convergence with probability is easily obtained because diversity is not considered. However, diversity cannot be guaranteed. By combining the convergence with diversity, this paper presents a new definition for the finite representation of a Pareto set, the B-Pareto set, and a convergence metric for MOEAs. Based on a new archive-updating strategy, the convergence of one such MOEA to the B-Pareto sets of MOPs is proved. Numerical results show that the obtained B-Pareto front is uniformly distributed along the Pareto front when, according to the new definition of convergence, the algorithm is convergent.     

Achieving balance between proximity and diversity in multi-objective evolutionary algorithm

Currently, an alternative framework using the hypervolume indicator to guide the search for elite solutions of a multi-objective problem is studied in the evolutionary multi-objective optimization community very actively, comparing to the traditional Pareto dominance based approach. In this paper, we present a dynamic neighborhood multi-objective evolutionary algorithm based on hypervolume indicator (DNMOEA/HI), which benefits from both Pareto dominance and hypervolume indicator based frameworks. DNMOEA/HI is featured by the employment of hypervolume indicator as a truncation operator to prune the exceeded population, while a well-designed density estimator (i.e., tree neighborhood density) is combined with the Pareto strength value to perform fitness assignment. Moreover, a novel algorithm is proposed to directly evaluate the hypervolume contribution of a single individual. The performance of DNMOEA/HI is verified on a comprehensive benchmark suite, in comparison with six other multi-objective evolutionary algorithms. Experimental results demonstrate the efficiency of our proposed algorithm. Solutions obtained by DNMOEA/HI well approach the Pareto optimal front and are evenly distributed over the front, simultaneously.     

Convergence analysis of a self-adaptive multi-objective evolutionary algorithm based on grids

Evolutionary algorithms have been successfully applied to various multi-objective optimization problems. However, theoretical studies on multi-objective evolutionary algorithms, especially with self-adaption, are relatively scarce. This paper analyzes the convergence properties of a self-adaptive (μ+1)-algorithm. The convergence of the algorithm is defined, and general convergence conditions are studied. Under these conditions, it is proven that the proposed self-adaptive (μ+1)-algorithm converges in probability or almost surely to the Pareto-optimal front.     

The assessment of evolutionary algorithms for analyzing the positional accuracy and uncertainty of maps

Pre-geodetic maps are an important part of our cultural heritage and a potential source of information for historical studies. Historical cartography should be evaluated in terms of precision and uncertainty prior to their use in any application. In the last decade, the majority of papers that address multi-objective optimization employed the concept of Pareto optimality. The goal of Pareto-based multi-objective strategies is to generate a front (set) of nondominated solutions as an approximation to the true Pareto-optimal front. This article proposes a solution for the problems of multi-objective accuracy and uncertainty analysis of pre-geodetic maps using four Pareto-based multi-objective evolutionary algorithms: HVSEA, NSGAII, SPEAII and msPESA. “The Geographic Atlas of Spain (AGE)” by Tomas Lopez in 1804 provides the cartography for this study. The results obtained from the data collected from the kingdoms of Extremadura and Aragon, sheets of maps (54-55-56-57) and (70-71-72-73), respectively, demonstrate the advantages of these multi-objective approaches compared with classical methods. The results show that the removal of 8% of the towns it is possible to obtain improvements of approximately 30% for HVSEA, msPESA and NSGAII. The comparison of these algorithms indicates that the majority of nondominated solutions obtained by NSGAII dominate the solutions obtained by msPESA and HVSEA; however, msPESA and HVSEA obtain acceptable extreme solutions in some instances. The Pareto fronts based on multi-objective evolutionary algorithms (MOEAs) are a better alternative when the uncertainty of map analyzed is high or unknown. Consequently, Pareto-based multi-objective evolutionary algorithms establish new perspectives for analyzing the positional accuracy and uncertainty of maps.     

混合分解和强度帕累托多目标进化算法

在多目标进化优化中,使用分解策略的基于分解的多目标进化算法(MOEA/D)时间复杂度低,使用〖BP(〗强度帕累托策略的〖BP)〗强度帕累托进化算法-2(SPEA2)能得到分布均匀的解集。结合这两种策略,提出一种新的多目标进化算法用于求解具有复杂、不连续的帕累托前沿的多目标优化问题(MOP)。首先,利用分解策略快速逼近帕累托前沿;然后,利用强度帕累托策略使解集均匀分布在帕累托前沿,利用解集重置分解策略中的权重向量集,使其适配于特定的帕累托前沿;最后,利用分解策略进一步逼近帕累托前沿。使用的反向世代距离(IGD)作为度量标准,将新算法与MOEA/D、SPEA2和paλ-MOEA/D在12个基准问题上进行性能对比。实验结果表明该算法性能在7个基准问题上最优,在5个基准问题上接近于最优,且无论MOP的帕累托前沿是简单或复杂、连续或不连续的,该算法均能生成分布均匀的解集。     

基于距离收敛量和历史信息密度的多目标进化算法

在筛选个体的过程中,多目标进化算法大都利用非支配信息和密度信息评价个体。但当个体互为非支配关系时,上述信息就难以区分个体的优劣从而影响算法性能。为了改善上述情况,本文提出了一种基于距离收敛量和历史信息密度的多目标进化算法。距离收敛量可以在非支配信息不能区分个体时评价个体的收敛性;历史信息密度可以更精确的提供个体多样性信息。在与三个先进的多目标进化算法的对比实验中,新算法的求解质量明显优于对比算法。     

多目标优化的演化算法

近年来．多目标优化问题求解已成为演化计算的一个重要研究方向，而基于Pareto最优概念的多目标演化算法则是当前演化计算的研究热点．多目标演化算法的研究目标是使算法种群快速收敛并均匀分布于问题的非劣最优域．该文在比较与分析多目标优化的演化算法发展的历史基础上，介绍基于Pareto最优概念的多目标演化算法中的一些主要技术与理论结果，并具体以多目标遗传算法为代表，详细介绍了基于偏好的个体排序、适应值赋值以及共享函数与小生境等技术．此外，指出并阐释了值得进一步研究的相关问题．     

Multi-objective reactive power market clearing in competitive electricity market using HFMOEA

This paper presents an application of a hybrid fuzzy multi-objective evolutionary algorithm (HFMOEA) for solving a highly constraint, mixed integer type, complex multi-objective reactive power market clearing (RPMC) problem for the competitive electricity market environment. In HFMOEA based multi-objective optimization approach, based on the output of a fuzzy logic controller crossover and mutation probabilities are varied dynamically. It enhances stochastic search capabilities of HFMOEA. In multi-objective RPMC optimization framework, two objective functions namely the total payment function (TPF) for reactive power support from generators and synchronous condensers and the total real transmission loss (TRTL) are minimized simultaneously for clearing the reactive power market. The proposed HFMOEA based multi-objective RPMC scheme is tested on a standard IEEE 24 bus reliability test system and its performance is compared with five other multi-objective evolutionary techniques such as MOPBIL, NSGA-II, UPS-EMOA and SPEA-2 and a new extended form of NSGA (ENSGA-II). Applying all these six evolutionary techniques, a detailed statistical analysis using T-test and boxplots is carried out on three performance metrics (spacing, spread and hypervolume) data for RPMC problem. The obtained simulation results confirm the overall superiority of HFMOEA to generate better Pareto-optimal solutions with higher convergence rate as compared to above mentioned algorithms. Further, TPF and TRTL values corresponding to the best compromise solutions are obtained using said multi-objective evolutionary techniques. These values are compared with one another to take better market clearing decisions in competitive electricity environment.     

On decomposition methods in interactive user-preference based optimization

Evolutionary multi-objective optimization (EMO) methodologies have been widely applied to find a well-distributed trade-off solutions approximating to the Pareto-optimal front in the past decades. However, integrating the user-preference into the optimization to find the region of interest (ROI) [1] or preferred Pareto-optimal solutions could be more efficient and effective for the decision maker (DM) straightforwardly. In this paper, we propose several methods by combining preference-based strategy (like the reference points) with the decomposition-based multi-objective evolutionary algorithm (MOEA/D) [2], and demonstrate how preferred sets or ROIs near the different reference points specified by the DM can be found simultaneously and interactively. The study is based on the experiments conducted on a set of test problems with objectives ranging from two to fifteen objectives. Experiments have proved that the proposed approaches are more efficient and effective especially on many-objective problems to provide a set of solutions to the DM's preference, so that a better and a more reliable decision can be made.     

一类新型动态多目标鲁棒进化优化方法

传统动态多目标优化问题（Dynamic multi-objective optimization problems,DMOPs）的求解方法,通常需要在新环境下,通过重新激发寻优过程,获得适应该环境的Pareto最优解.这可能导致较高的计算代价和资源成本,甚至无法在有限时间内执行该优化解.由此,提出一类寻找动态鲁棒Pareto最优解集的进化优化方法.动态鲁棒Pareto解集是指某一时刻下的Pareto较优解可以以一定稳定性阈值,逼近未来多个连续动态环境下的真实前沿,从而直接作为这些环境下的Pareto解集,以减小计算代价.为合理度量Pareto解的环境适应性,给出了时间鲁棒性和性能鲁棒性定义,并将其转化为两类鲁棒优化模型.引入基于分解的多目标进化优化方法和无惩罚约束处理方法,构建了动态多目标分解鲁棒进化优化方法.特别是基于移动平均预测模型实现了未来动态环境下适应值的多维时间序列预测.基于提出的两类新型性能评价测度,针对8个典型动态测试函数的仿真实验,结果表明该方法得到满足决策者精度要求,且具有较长平均生存时间的动态鲁棒Pareto最优解.     

Multi-objective optimization of expensive electromagnetic simulation models

Vast majority of practical engineering design problems require simultaneous handling of several criteria. For the sake of simplicity and through a priori preference articulation one can turn many design tasks into single-objective problems that can be handled using conventional numerical optimization routines. However, in some situations, acquiring comprehensive knowledge about the system at hand, in particular, about possible trade-offs between conflicting objectives may be necessary. This calls for multi-objective optimization that aims at identifying a set of alternative, Pareto-optimal designs. The most popular solution approaches include population-based metaheuristics. Unfortunately, such methods are not practical for problems involving expensive computational models. This is particularly the case for microwave and antenna engineering where design reliability requires utilization of CPU-intensive electromagnetic (EM) analysis. In this work, we discuss methodologies for expedited multi-objective design optimization of expensive EM simulation models. The solution approaches that we present here rely on surrogate-based optimization (SBO) paradigm, where the design speedup is obtained by shifting the optimization burden into a cheap replacement model (the surrogate). The latter is utilized for generating the initial approximation of the Pareto front representation as well as further front refinement (to elevate it to the high-fidelity EM simulation model level). We demonstrate several application case studies, including a wideband matching transformer, a dielectric resonator antenna and an ultra-wideband monopole antenna. Dimensionality of the design spaces in the considered examples vary from six to fifteen, and the design optimization cost is about one hundred of high-fidelity EM simulations of the respective structure, which is extremely low given the problem complexity.     

DOPGA: a new fitness assignment scheme for multi-objective evolutionary algorithms

In this article, a new fitness assignment scheme to evaluate the Pareto-optimal solutions for multi-objective evolutionary algorithms is proposed. The proposed DOmination Power of an individual Genetic Algorithm (DOPGA) method can order the individuals in a form in which each individual (the so-called solution) could have a unique rank. With this new method, a multi-objective problem can be treated as if it were a single-objective problem without drastically deviating from the Pareto definition. In DOPGA, relative position of a solution is embedded into the fitness assignment procedures. We compare the performance of the algorithm with two benchmark evolutionary algorithms (Strength Pareto Evolutionary Algorithm (SPEA) and Strength Pareto Evolutionary Algorithm 2 (SPEA2)) on 12 unconstrained bi-objective and one tri-objective test problems. DOPGA significantly outperforms SPEA on all test problems. DOPGA performs better than SPEA2 in terms of convergence metric on all test problems. Also, Pareto-optimal solutions found by DOPGA spread better than SPEA2 on eight of 13 test problems.     

Improving convergence of evolutionary multi-objective optimization with local search: a concurrent-hybrid algorithm

A local search method is often introduced in an evolutionary optimization algorithm, to enhance its speed and accuracy of convergence to optimal solutions. In multi-objective optimization problems, the implementation of local search is a non-trivial task, as determining a goal for local search in presence of multiple conflicting objectives becomes a difficult task. In this paper, we borrow a multiple criteria decision making concept of employing a reference point based approach of minimizing an achievement scalarizing function and integrate it as a search operator with a concurrent approach in an evolutionary multi-objective algorithm. Simulation results of the new concurrent-hybrid algorithm on several two to four-objective problems compared to a serial approach, clearly show the importance of local search in aiding a computationally faster and accurate convergence to the Pareto optimal front.