Abstract
In dynamic multiobjective optimization problems, the environmental parameters may change over time, which makes the Pareto fronts shifting. To address the issue, a common idea is to track the moving Pareto front once an environmental change occurs. However, it might be hard to obtain the Pareto optimal solutions if the environment changes rapidly. Moreover, it may be costly to implement a new solution. By contrast, robust Pareto optimization over time provides a novel framework to find the robust solutions whose performance is acceptable for more than one environment, which not only saves the computational costs for tracking solutions, but also minimizes the cost for switching solutions. However, neither of the above two approaches can balance between the quality of the obtained nondominated solutions and the computation cost. To address this issue, environmentdriven hybrid dynamic multiobjective evolutionary optimization method is proposed, aiming to fully use strengths of TMO and RPOOT under various characteristics of environmental changes. Two indexes, i.e., the frequency and intensity of environmental changes, are first defined. Then, a criterion is presented based on the characteristics of dynamic environments and the switching cost of solutions, to select an appropriate optimization method in a given environment. The experimental results on a set of dynamic benchmark functions indicate that the proposed hybrid dynamic multiobjective evolutionary optimization method can choose the most rational method that meets the requirements of decision makers, and balance the convergence and robustness of the obtained nondominated solutions.
Introduction
In many practical applications, such as scheduling [1], controller optimization [2, 3] and path planning [4, 5], we focus on more than one objective that contradicts each other. More especially, the key parameters, the number of objectives and constrains may change over time [6,7,8,9], forming dynamic multiobjective optimization problems (DMOPs) [10]. For example, in a hydrothermal power generation systems, the total fuel cost of thermal generation and emission properties are minimized, while satisfying all constraints in the hydraulic and power system networks, so as to allocate power reasonably to the hydroelectric and thermal generating units. It is in essence a dynamic optimization problem due to the timevarying power demand [10]. Apparently, tracking the optimal solution in time as any dynamic factor occurs is a challenging task for DMOPs.
To address DMOPs, many metaheuristic methods [11,12,13,14,15,16] have been introduced that can be categorized into two classes. One is to retrigger the multiobjective optimization process as a new environment appears, with the purpose of finding the Paretooptimal solutions more close to the new true Pareto front as soon as possible. We call this approach tracking moving Paretooptimum (TMO). The key issue on TMO is to keep the better diversity of population as a new environment appear. Rich studies have been done on change response techniques, including environmental detection [1, 6, 8], immigrantlearning [11], prediction and memory strategies [14, 15, 17,18,19,20]. All these prove that TMO is a powerful method to solve DMOPs with slowlychanging environments and less switching cost of solutions. However, in many real world optimization problems, tracking the new Paretooptima every time the environment changes is impractical due to the limited computation resources for optimization or the expensive switching cost from the previous optima [21]. To save the computation and reduce switching times, Yu et al. [22] firstly proposed a novel framework to find robust optimum over time (ROOT) for dynamic scalar optimization problems, in which a robust solution implemented in the current situation also has the acceptable convergence and can be kept in use after the environment changes. Jin et al. [23] presented a quantitative description of robustness and a general framework for finding ROOT. Following that, Chen et al. [24] presented a practical definition of finding robust Paretooptima over time (RPOOT) for DMOPs. A Paretooptimal solution that was found in the current environment and has the acceptable convergence in the subsequent environments are termed as a robust candidate [25]. Apparently, reusing the robust solution in the successive environments saves the computation and switching cost. But the robustness of a candidate will become worse as the environment changes intensely [26]. Once no historical Paretooptimal solution has the satisfactory performance on at least one objective in the sequence environments, TMO will be an effective alternative to RPOOT. Consequently, TMO and RPOOT are both successful problemsolvers for DMOPs, however, fit for various environmental changes.
In benchmark test suites for dynamic optimization, the environments change over time with different way, such as linear change [11, 27, 28], chaotic change [29], and stochastic change [30]. Moreover, the environmental change occurs with various frequencies and intensities. For example, in the dynamic scheduling problems of airport fuel filling vehicles [31] three objectives were taken into account, including minimizing the length of the whole routes and the number of running vehicles, as well as minimizing the task quantity difference between vehicles. Because the takeoff and landing times of each aircraft are always changing in terms of weather, congestion situation and other dynamic factors that may occur irregularly, the refueling vehicles routing problem is essentially a DMOP with complex environmental changes, the corresponding frequency and intensity of environmental changes are not fixed. During finding the optimal scheduling scheme for all refueling vehicles under the uncertain delay time of the aircrafts, traditional TMO may not meet the needs of a realtime task due to the frequent adjustment of vehicle routing, while RPOOT can only provide a suboptimal scheme with robustness over time. Based on this, an environmentdriven hybrid dynamic multiobjective evolutionary optimization algorithm is presented in this paper, with the purpose of effectively balancing the quality of Paretooptima and switching cost. In the proposed method, a prediction model is built to estimate the frequency and intensity of environmental changes based on their historical information. Based on the characteristics of dynamic environments and the switching cost of solutions, a selection criterion is designed to adaptively trigger TMO or RPOOT.
The rest of the paper is organized as follows. The main ideas of TMO and RPOOT are illustrated in “The main ideas of TMO and RPOOT” section. “Indexes measuring environmental changes” section defines various parameters that represent the features of environmental changes. Based on this, a generic framework of hybrid dynamic multiobjective evolutionary optimization method is developed and the condition for selecting one of the two methods is given in “Proposed algorithm” section. In “Experimental study” section, the experimental results are analyzed under different environmental changes. Finally, a conclusion of the paper and future work are given in “Conclusion” section.
The main ideas of TMO and RPOOT
Without loss of generality, a DMOP with timevarying parameters can be described as follows.
where \({\pmb x}=(x_1,x_2,\ldots ,x_n)\in {\pmb {\Omega }}\subset {\pmb R}^{n}\) represents the decision vector and \({\pmb {\Omega }}\) is the ndimensional decision space. \({\pmb F}=(f_1,f_2,\ldots ,f_m)\in {\pmb {\Lambda }}\subset {\pmb R}^{m}\) is the objective function vector and \({\pmb {\Lambda }}\) is the mdimensional objective space. \(\pmb {\alpha }^t\) denotes the environmental parameter changing over time. In practice, the environmental changes generally occur at some discontinuous time points, thus, the timevarying parameters can be discretized to \(\pmb {\alpha }^k,k=1,2,\ldots ,N\). Assume that the dynamic parameters vary with frequency \(f^k=1/\tau ^k\), and \(\pmb {\alpha }^k\) remains constant when \(t\in [\sum _{j=0}^{k1}{\tau ^j},\sum _{j=0}^{k}{\tau ^j}]\). \(\tau ^j\) is the duration of the jth environment and \(\tau ^0=0\). Following that, a DMOP is transformed to N static MOPs, denoted as \(\left\langle \min {\pmb F}({\pmb x},\pmb {\alpha }^1),\min {\pmb F}({\pmb x},\pmb {\alpha }^2),\ldots ,\min {\pmb F}({\pmb x},\pmb {\alpha }^N) \right\rangle \).
To solve the abovementioned DMOPs, most research has focused on tracking the new Pareto front with a fast convergence speed once an environmental change occurs. More specifically, it is essential for a TMObased dynamic evolutionary multiobjective algorithm to detect the environmental changes in time, generate an initial population using the knowledge acquired from the previous environments, and locate the new Pareto front as soon as possible. In particular, evolutionary algorithms and other metaheuristics, such as multiobjective genetic algorithms, particle swarm optimization and differential evolution [11, 27, 32,33,34,35,36,37,38], have been developed to follow the new Paretooptimal solutions quickly. A generic framework of TMO is shown in Algorithm 1.
Different from TMO, the goal of RPOOTbased dynamic multiobjective optimization algorithms is to find the robust Paretooptimal solutions, expressed by RPS \(=\left\langle \mathrm{RPS}(1)\right. \),\(\left. \mathrm{RPS}(2),\ldots ,\mathrm{RPS}(L)\right\rangle (1\le L\le N)\), which have the acceptable performance in more than one environment. To this end, two indexes have been defined to evaluate the robustness of an individual [24]. One is robustness for optimality, which measures the degree of \({\pmb x}_i^j \in \mathrm{{RPS}}(i)\) approximate to the true Pareto fronts in T consecutive environments, denoted as \({\pmb F}^\mathrm{ave}({\pmb x}_i^j,\pmb {\alpha }^k)\). T is called the time window and preset by a decision maker according to his/her expectation for the adaptability of an individual to environmental changes.
The other is the temporal robustness, denoted as \(L_i\), which reflects the survival time of RPS(i) in the subsequent environments. Let \(\eta \) be a preset threshold that represents the maximum acceptable increment of the fitness value. Denote \({\hat{{\pmb F}}}({\pmb x}_i^j,\pmb {\alpha }^{k+l({\pmb x}_i^j)}))\) as the estimated fitness of \({\pmb x}_i^j\) in the \(k+l\) environments, one has
where \(\Delta (l({\pmb x}_i^j)\) represents the relative fitness difference under the adjacent dynamic environment about an individual \({\pmb x}_i^j\). Here, \({\pmb x}_i^j\) comes from the robust Pareto solutions RPS(i). The smaller the difference is, the solution can adapt to the new environment better. \(\bar{l}({\pmb x}_i^j)\) is the maximum survival time for \({\pmb x}_i^j\) to meet the fitness threshold. The survival time of each solution in RPS(i) should be larger or equal to \(L_i\).
Taking the robustness as the objective, the main algorithm steps of RPOOTbased dynamic multiobjective evolutionary optimization method are listed in Algorithm 2.
Apparently, both TMO and RPOOT are effective problemsolvers for DMOPs, which provide the Paretooptimal solutions with different convergence and switching cost. How to choose the most suited method in the presence of a certain environmental change is still an open and challenging issue.
Indexes measuring environmental changes
In DMOPs, the environmental parameters change over time with various intervals and increments. To quantitatively measure the changes, two indexes, i.e., the frequency and intensity of environmental changes, are presented. Most existing research focuses on DMOPs where the environment changes with the same interval or intensity. However, the dynamism factors in practical applications may occur irregularly, which are described by the environmental parameters that change over time aperiodically, leading to difficulties in converging to the true Pareto front as soon as possible under each environment.
The frequency and intensity of environmental changes
The frequency of environmental changes, denoted as \(f^k\), reflects how many new environments occur within a given period of time. To be specific, \(f^k=\frac{1}{\tau ^k}\) and the environmental parameters remain unchanged under the kth environment. A smaller \(f^k\) means that the dynamic factors have an occasional influence on the optimization problems. So far, only static \(f^k\) has been considered in most dynamic optimization problems. However, the environment in practical applications may change with variable intervals. Based on this, the frequencies of environmental changes are expressed by \((f^1, f^2, \ldots , f^{N})\), and \(f^k\) may differ from \(f^{k+1}\) depending on the actual situation.
The environmental parameter, \(\pmb {\alpha }^k\), has a direct impact on the landscape of the optimizaiton problem under the kth environment. Assume that the increment of the parameter under two adjacent environments is denoted as \(\Delta {\pmb {\alpha }^{k+1}}=\pmb {\alpha }^{k+1}\pmb {\alpha }^k\). For various DMOPs or a DMOP under different environments, the same increment may generate distinct landscapes due to the nonlinear relationship of \(\pmb {\alpha }^k\) to \(F(\pmb x,\pmb {\alpha }^t)\). In order to accurately measure the influence of changing environmental parameters over time on the landscape, the intensity of environmental changes is defined as follows:
Let \(N_{P^k}\) be the population size. A larger \(s^{k+1}\) means that the landscape may significantly vary with the environmental parameter in the adjacent environments. Under these circumstances, the robust Paretooptimal solutions are difficult to get satisfactory convergence in the adjacent environments, thus, RPOOT is not a wise choice. Thus, it is vital to properly estimate the intensity of changes of the future environments, which determines whether the TMO or RPOOT approach should be adopted.
Taking a benchmark function, FDA3 [27], as an example, the true Pareto fronts under three adjacent environments are shown in Fig. 1. All environmental parameters change over time with the same increment and \(\Delta {\pmb {\alpha }^{k+1}}\) is set to 0.1 or 0.2, respectively. Under the same \(\Delta {\pmb {\alpha }^{k+1}}\), three Pareto fronts corresponding to 1st, 2nd and 3rd environments are parallel, however, the intensity of the latter environmental changes is clearly larger than that of the former one. By comparing the Pareto fronts shown in Fig. 1a, b, the environmental parameter changes with a larger increment result in the more significant shift of the landscape, and the intensity of the environmental changes is more severe. Apparently, the Paretooptimal solution having the acceptable convergence under the dynamic environments shown in Fig. 1a can be found by RPOOT because \(s^2\) and \(s^3\) are both smaller than \(\eta =0.4\). By contrast, RPOOT can not obtain the satisfactory Paretooptimal solutions in any environment shown in Fig. 1b due to the larger intensity. Hence, the environmental parameters directly influence the variation of the landscape in various environments.
To predict the environmental parameters in the future
For a DMOP with timevarying environmental parameters, the frequency and intensity of environmental changes determine which of the two approaches should be employed as a more effective one in future environments. To this end, it is necessary to accurately estimate the abovementioned characteristics of the environments that are changing.
Both of the characteristics are related to \(\pmb {\alpha }^k\). In particular, the intensity of the \((k+1)\)th environmental change can be estimated by Eq. (6) based on the environmental parameters in the next environment, expressed by \(\pmb {\alpha }^{k+1}\). Hence, it is assumed that the future environmental parameters can be predicted. Until now, most studies assume that the environmental parameters linearly change over time [11, 27]. However, in the actual DMOPs, the environmental parameters may change periodically, randomly, or chaotically.
To reliably predict the environmental parameters in the future environments, Autoregressive Integrated Moving Average Model (ARIMA) [39], a widelyused time series prediction method, is employed. Assume that the timevarying environmental parameters form a time series, expressed by \(\{\pmb {\alpha }^1,\pmb {\alpha }^2,\ldots ,\pmb {\alpha }^k\}\). After smoothing it to a stationary one, the autoregressive, the moving average or the autoregressive moving average is selected to build the ARIMA(p, d, q) model, which is then used to forecast the future environmental parameters. The detailed modeling process is illustrated as follows.

(1)
Judge the stationarity of the time series \(\{\pmb {\alpha }^k\}\) by the Augmented Dickey–Fuller (ADF) Test [39].

(2)
If \(\{\pmb {\alpha }^k\}\) is nonstationary, the following smoothing process is iterated until a stable time series, denoted as \(\{\nabla ^n \pmb {\alpha }^k\}\), is obtained. Let d be the differential times.
$$\begin{aligned} {\text {1order difference:}}&\nabla \pmb {\alpha }^k=\pmb {\alpha }^{k+1}\pmb {\alpha }^k \end{aligned}$$(8a)$$\begin{aligned} {\text {norder difference:}}&\nabla ^n \pmb {\alpha }^k=\nabla ^{n1} \pmb {\alpha }^{k+1}\nabla ^{n1} \pmb {\alpha }^k \end{aligned}$$(8b) 
(3)
Given \(\{\nabla ^n \pmb {\alpha }^k\}\), if its partial correlation function has the truncation property and the autocorrelation function has the trailing edge, AR(p) is employed to build the prediction model, and p is the autoregressive term. By contrast, MA(q) is suitable for \(\{\nabla ^n \pmb {\alpha }^k\}\), which has a trailing edge of its partial correlation function and the truncation of the autocorrelation function. q is the moving average term. Once both the partial correlation and autocorrelation functions have a trailing edge, ARMA(p, q) is used as the prediction model.

(4)
The environmental parameters in the future environments are predicted by the above ARIMA(p, d, q) model.
Proposed algorithm
Once the environmental parameters of a DMOP have changed, it is necessary to select one of the two approaches to dynamic multiobjective optimization method according to the predicted characteristics of environmental changes, with the purpose of finding the Paretooptima or robust ones that meet the requirements of decision makers. To this end, a hybrid dynamic multiobjective evolutionary optimization algorithm is proposed.
Definition of switching cost
Neither the TMObased nor RPOOTbased optimization approaches take into account switching costs, the former switches to a new solution at every dynamic moment, while the latter switches to the new solutions only when the solution does not satisfy robustness. In the real world dynamic optimization problems, such as production scheduling and path planning [1, 4], an optimal solution found in the new environment may remarkably differ from the historical one, resulting in the huge cost for adjusting the related human or resources. In this situation, the newlyobtained optimal solution is unavailable due to the unacceptable costs incurred in switching solution.
To get an executable optimal solution, Huang et al. [21] took switching cost as an objective, and presented a multiobjective optimization framework for robust optimization over time. Furthermore, ROOT/SCII [40] is proposed to simultaneously maximize the robustness and minimize the switching cost, and select a solution from the obtained Pareto set to be used in the new environment. Yazdani [41, 42] considered the timelinkage characteristic of dynamic optimization problems, and proposed a new semi robust optimization over time, with the purpose of balancing switching cost and the quality of solutions. Based on the abovementioned switching cost presented for dynamic singleobjective optimization problems, we define the improved switching cost for the Paretooptimal solutions from the kth to the \((k+1)\)th dynamic environment, denoted as \(sc^{k+1}\), as follows.
In above formula, \(P^k\) represents the Paretooptimal solution set in the kth environment, and \(N_{P^k}\) is its size. \({\pmb x}'\) is an Paretooptimum in the \((k+1)\)th environment. \(sc^{k+1}\) represents the average relative error of the Pareto solutions switching from the kth environment to the \((k+1)\)th environment. The switching cost of solutions can provide decision makers the information for determining whether the solution should be switched or not.
Selection criteria
TMO and RPOOT are two different problemsolvers for DMOPs. In TMO, the optimization process will be triggered whenever an environmental change is detected. If the environments vary with a short interval, there is insufficient time for the population to converge to the true Pareto front. In this case, RPOOT can provide feasible and satisfactory solutions derived from previous environments without finding new ones in the current environment. Although no cost will be spent on tracking the new Paretooptimal solutions, the robust ones found by RPOOT are just acceptable suboptimal in the subsequent environments. More specifically, the Pareto front of the historical Paretooptimal solutions may be far away from the true one in the current environment, especially for DMOPs with strong environmental changes. In this instance, TMO will be employed instead of RPOOT, with the purpose of obtaining new optimal solutions. Therefore, the dynamic characteristics of environmental changes and switching cost are both key factors that determine which dynamic multiobjective optimization method should be adopted in the next environment.
Suppose that \(c^k_f\), \(c^k_s\) and \(c^k_{sc}\) are the coefficients for the frequency and intensity of environmental changes, as well as switching cost, respectively. \({\delta }_f\), \({\delta }_s\) and \({\delta }_{sc}\) are the corresponding thresholds preset by a decision maker.
\(c^k_f=1\) and \(c^k_s=1\) represent that the environment changes significantly within a short time period and low intensities. Similarly, \(c^k_{sc}=1\) indicates that switching cost of a solution is too high to be accepted by decision makers.
As we known, RPOOTbased dynamic robust multiobjective evolutionary optimization method is suited for solving DMOPs with frequent, but weak environmental changes, namely, \(c^k_f=1\) and \(c^k_s=1\). In this case, tracking the Paretooptima in the current environment during the limited time is difficult. On the contrary, if the environments vary with a large interval or strong intensity, that is, \(c^k_f=0\) or \(c^k_s=0\), DMOP in each environment can be regarded as a static MOP. Thus, TMObased dynamic multiobjective evolutionary optimization method has enough time to find the Paretooptimal solutions approximating to the true one. Furthermore, if the cost of switching the solutions to be implemented in two consecutive environments is relatively low, the obtained new Paretooptimal solutions are acceptable. Otherwise, the suboptimal Pareto solutions approximating to the optimal ones in the last environment will be employed. Based on this, the criteria for choosing dynamic multiobjective optimization methods are presented as follows.
Selection criteria In the kth environment,

(1)
If \(c^k_s=0\), TMObased dynamic multiobjective evolutionary optimization method is employed.

(2)
if \(c^k_s=1\) and \(c^k_f=1\), RPOOTbased dynamic robust multiobjective evolutionary optimization method is adopted.

(3)
if \(c^k_s=1\) and \(c^k_f=0\), TMObased dynamic multiobjective evolutionary optimization method is employed.

(a)
if \(c^k_{sc}=1\), the suboptimal solution close to the optimal ones obtained in the last environment is used in the current problem.

(b)
if \(c^k_{sc}=0\), the new Paretooptimal solutions are employed.

(a)
Overall framework
The pseudocode of hybrid dynamic multiobjective evolutionary optimization algorithm (HDMEOA) is shown in Algorithm 3. The key issues are illustrated one by one as follows.

(1)
Construct the time series of environmental parameters In the kth environment, the time series of the environmental parameters denoted as \(\{\pmb {\alpha }^1,\pmb {\alpha }^2,\ldots ,\pmb {\alpha }^{k}\}\) are formed by the historical ones. The corresponding frequencies of environmental changes are \((f^1, f^2, \ldots , f^{k})\).

(2)
Predict the environmental parameters Based on \(\{\pmb {\alpha }^1,\pmb {\alpha }^2,\ldots ,\pmb {\alpha }^{k}\}\), the ARIMA prediction model is built and employed to estimate the future environmental parameters \(\hat{\pmb {\alpha }}^{k+1}, \ldots , \hat{\pmb {\alpha }}^{k+T1}\). Following that, the fitness values of an individual, expressed by \(F(\pmb {x},\hat{\pmb {\alpha }}^{k+1}),\ldots , F(\pmb {x},\hat{\pmb {\alpha }}^{k+T1})\), are calculated.

(3)
Choose the evolutionary optimization method The intensity of environmental changes is estimated in terms of predictive fitness values. Based on the estimated dynamic characteristics and switching cost, TMO or RPOOTbased dynamic multiobjective evolutionary method is selected to obtain satisfactory Pareto solutions in the current environment according to the designed criteria.
Experimental study
To verify the effectiveness of the proposed HDMEOA framework, three groups of experiments are designed. The effectiveness of the prediction model is first analyzed in the presence of linear, chaotic and stochastic environmental changes. Following that, the performance of HDMEOA is further compared with TMO and RPOOTbased dynamic multiobjective evolutionary optimization methods, as shown in Algorithms 1 and 2, respectively. Three kinds of methods all employ multiobjective evolutionary algorithm based on decomposition (MOEA/D) [43] as the optimizer. The ttest is carried out to indicate significance between different results at the 0.05 significance level [29, 44]. If there is a significant difference between the two, the observation is labeled as ‘\(+\)’ after the value. Otherwise, there is a ‘−’ after the value. All experiments are carried out on a PC with Intel Core i52430M CPU 2.4 GHz, 16 GB RAM, Windows 10 operating system, and Matlab R2016a.
Benchmark functions and performance metrics
All experiments are performed on eight commonlyused dynamic benchmark functions, including FDA1FDA5 [27] and DMOP1DMOP3 [11]. Their definition and characteristics are presented in Table 1, and the main parameters of HDMEOA proposed in this work are listed in Table 2.
To synthetically evaluate the convergence and robustness of the Paretooptimal solutions obtained by TMO and the robust ones found by RPOOT, the mean robust survival time (MRST) and mean robust inverse generation distance (MRIGD) defined by Chen et al. [24] are introduced as the metrics.
Mean robust survival time The MRST of the Paretooptimal solutions obtained by TMO or RPOOT under all environments reflects their adaptability to the dynamic environments. Let \(L_i\) be the survival time of the ith Paretooptimal solution. In particular, \(L_i=1\) means that the Paretooptimal solution was obtained by TMO.
Mean robust inverse generation distance The MRIGD comprehensively measures the convergence and distribution of the Paretooptimal solutions within their survival time.
Prediction accuracy
Environmentdriven HDMEOA provides a generic framework for various problemsolvers of DMOPs, with the purpose of obtaining the Paretooptima that meet the requirements of a decision maker under a given environment. To fully verify the effectiveness of the proposed framework, three types of environmental changes that commonly appear in actual DMOPs are taken into account, in which the environmental parameters change over time with the linear [11, 27], chaotic and Stochastic [30] mode as shown in Fig. 2.
Linear change Assume that the dynamic environmental parameters start from 0, and increase linearly with a fixed increment of 0.2 [11, 26]. Since \(N=50\), the range of \({\alpha }^k\in [0,10]\), as shown in Fig. 2a.
Chaotic change Chaos is derived from nonlinear dynamical systems, whose trajectory is determined by the initial value and the chaotic mapping parameters [29] as follows.
In the experiment, the logistic parameter \(\mu =4\), and the initial value \(x_0=0.6\). Following (15), the environmental parameter \(\alpha ^k=10x_k\), and \({\alpha }^k\in [0,10]\), as shown in Fig. 2b.
Stochastic change The environmental parameters is generated by a random number satisfying uniform distribution in [0,10], as shown in Fig. 2c.
For the above three environmental changes, the future environmental parameters are estimated by the ARIMAbased prediction model. As shown in Fig. 3, under a dynamic time step \(k = 19\), the real and predicted fitness values are compared in the future T adjacent environments. Apparently, the prediction performance under linear change is the best, and the mean square deviation is 8.8818e−16. The prediction results under chaos and stochastic change is similar, and their mean square deviations are 0.8258 and 0.7053, respectively. Thus, predicting the range of chaos and stochastic change is more feasible.
Performance comparison under linear environmental changes
Suppose that the environmental parameters \(\alpha ^k\in [0,10], k=1,2,\ldots ,N\) linearly increase with the fixed increment about 0.2. Here, \(N=50\) and \(\alpha ^0=0\). Under the above environments, the proposed algorithm is compared with TMO and RPOOTbased dynamic multiobjective evolutionary optimization methods. Figures 4, 5 and 6 depict the IGD and survival time indicators obtained by different algorithms parameters. Tables 3, 4 and 5 list the corresponding experimental results, where data are the average and standard deviation, the boldface ones are the best values.
By comparing the MRIGD of the three algorithms listed in Table 3, and the IGD of each time in Fig. 4, we can see that TMObased dynamic multiobjective evolutionary optimization method has the smaller MRIGD than the others in most cases, which indicates that the corresponding Paretooptimal solutions are the closest to the true Pareto front. By contrast, the robust Paretooptimal solutions achieved by RPOOT has the poorest convergence performance due to their acceptable suboptimal performance in the adjacent environments. In addition, the MRST values listed in Table 4 indicate that the mean survival time of the robust Pareto solutions achieved by RPOOT is much larger than that of TMO, meaning that RPOOT achieves acceptable solutions in more environments, is quicker in finding optimal solutions in a new environment, and incurs less switching cost than TMO. Apparently, neither of them is able to balance the quality and robustness of solutions.
Different from TMO and RPOOT, HDMEOA has achieved similar MRIGD values to TMO while achieving fewer robust Paretooptimal solutions than RPOOT except for Fun2. Taking Fun7 as an example, the Paretooptimal solutions obtained by HDMEOA and TMO have a similar MRIGD value (around 0.063), which is smaller than 0.1551 obtained by RPOOT. In particular, the proposed algorithm has the best MRIGD for Fun4 and Fun5, indicating the best convergence. Moreover, the number of environments in which TMO or RPOOT is adopted, respectively, in HDMEOA listed in Table 5 shows that TMO is employed in 44 out of 50 environments, and 2 robust Paretooptimal solutions are used in other environments. The mean robust survival time of HDMEOA is 1.064, which is shorter than that of RPOOT. Less robust Paretooptima over time promotes the quality of the solution set, but weakens their robustness.
To further compare the robustness of the three methods, Fig. 5 depicts the robust survival time of all Paretooptimal solutions obtained in each environment as the environmental parameters change linearly. Apparently, TMObased multiobjective evolutionary optimization method needs to track each true Pareto front. Thus, the survival time of all solutions is 1. By contrast, the robust candidates found by HDMEOA and RPOOT remain in use under more than one environment, consequently having the survival time larger than 1. More specifically, the robust Pareto fronts obtained by RPOOT have the longest survival time, which shows the strongest robustness.
In addition, the experimental results listed in above tables indicate that both HDMEOA and RPOOT obtained worse MRIGD values with the increase of \(\eta \), but their MRST values are longer than these obtained by TMO. Taking a closer look, we find that, more suboptimal solutions are acceptable as \(\eta =0.4\), resulting in the worse convergence but enhanced robustness. For HDMEOA, Fig. 6 depicts the survival time of all Paretooptimal solutions under various threshold values for the intensity of environmental changes. As \(\delta _s=0.4\), the survival time of each robust solution becomes larger, meaning better robustness, because RPOOT is triggered under more environments with severer changes of the landscape.
Performance comparison under chaotic and stochastic environmental changes
The chaotic change is more complex than the linear one, causing more intensive environmental changes. By comparing with Table 3, the experimental results listed in Table 6 show that the obtained Paretooptimal solutions have worse convergence under the environment with chaotic changes. As can be seen from Table 7, the survival time of HDMEOA is slightly shorter than that of RPOOT, but longer than that of TMO. In HDMEOA, \(c^k_s=0\) in most of the environments, and the TMObased multiobjective evolutionary optimization method is employed according to the proposed criteria, as shown in Table 8. Moreover, HDMEOA has achieved similar MRIGD values to those achieved by TMO except on Fun6, where both HDMEOA and TMO are both significantly better than RPOOT, indicating that the Paretooptimal solutions obtained by HDMEOA and TMO are closer to the true Pareto front.
Under the adjacent environments randomly change within a certain range, the intensity of environmental change may not satisfy the preset threshold, and then RPOOT is seldom triggered. As shown in Tables 9, 10 and 11, for all benchmarks except for Functions 2 and 4, TMObased dynamic multiobjective evolutionary optimization method is adopted in most dynamic time steps, but it is difficult to find the robust optimal solutions. The survival time of HDMEOA as shown in Table 10 is shorter than that of RPOOT, but longer than TMO. Also, we observe from Table 9 that MRIGD of the solution sets gotten from HDMEOA more approximate to that of TMO.
As shown in Tables 3, 6 and 10, the MRIGD values of the nondominated solutions found by RPOOT are much larger than those of the other two methods, implying the poor convergence. HDMEOA has much smaller MRIGD values and exhibits the simliar performance to TMO due to the proposed selection criteria, especially on Fun6. The Pareto sets of Fun2 and Fun4 do not change, while the corresponding true Pareto fronts vary with environmental changes. As \(\delta _s=0.4\), the number of robust Pareto fronts obtained by HDMEOA and RPOOT are almost the same and their mean robust survival times are longer, RPOOT is better suited for solving DMOPs having the similar characteristics as the above functions.
Conclusion
Traditional TMObased dynamic multiobjective evolutionary optimization methods may not be able to satisfactory solutions with small switching cost in the presence of frequent and severe environmental changes. In contrast to TMO, RPOOTbased dynamic robust multiobjective evolutionary optimization methods are developed to find robust Paretooptima whose performance is acceptable in a number of adjacent environments. However, both methods can not balance the quality of solutions and the cost for switching and computation. To address the above dilemma, an environmentdriven HDMEOA has been proposed in this paper. Firstly, two indexes, including the frequency and intensity of environmental changes are defined. Secondly, a criterion is presented based on the characteristic of dynamic environments and switching cost of solutions, with the purpose of selecting an appropriate method from TMO and RPOOT in each environment. To test the effectiveness of the proposed strategy, the experiments are designed based on eight benchmark functions under linear, chaotic and stochastic environmental changes. The statistical results reveal that the HDMEOA can effectively choose the more suited method (TMO or RPOOT) that meets the requirements of decision makers. It is very meaningful to strike a good balance between the convergence and robustness of the Paretooptimal solutions.
It is worth noting that only linear ,chaotic and stochastic environmental changes are considered in this paper, however, there exist other types of dynamic environmental changes in practice. It is interesting to study the influences and effects of the HDMEOA on real application dynamic optimal problems. Furthermore, predicting environmental changes accurately plays a key role in choosing the suited optimization methods from TMO and RPOOT. As we known, any prediction method has the different accuracy for dynamic problems with various kinds of environmental changes. For example, the ARIMA model used in this paper has a good prediction effect on linear change, but not on chaotic and stochastic changes. To solve this drawback, one may consider more prediction methods, such as [26, 44, 45], to track the dynamic environments with other nonlinear changes.
References
Deb K, Udaya BRN, Karthik S (2007) Dynamic multiobjective optimization and decisionmaking using modified NSGAII: a case study on hydrothermal power scheduling. Lect Notes Comput Sci 4403(1):803–817
Zhang Z (2008) Multiobjective optimization immune algorithm in dynamic environments and its application to greenhouse control. Appl Soft Comput 8(2):959–971
Mavrovouniotis M, Li C, Yang S (2017) A survey of swarm intelligence for dynamic optimization: algorithms and applications. Swarm Evol Comput 33:1–17
Guo Y, Cheng J, Luo S, Gong D, Xue Y (2018) Robust dynamic multiobjective vehicle routing optimization method. IEEE/ACM Trans Comput Biol Bioinf 15(6):1891–1903
Yang S, Cheng H, Wang F (2010) Genetic algorithms with immigrants and memory schemes for dynamic shortest path routing problems in mobile ad hoc networks. IEEE Trans Syst Man Cybern C 40(1):52–63
Liu R, Li J, Liu J, Jiao L (2020) A survey on dynamic multiobjective optimization. China J Comput 43(7):33
Nguyen T, Yao X (2012) Continuous dynamic constrained optimisationthe challenges. IEEE Trans Evol Comput 16(6):769–786
Liu R, Yang P, Liu J (2021) A dynamic multiobjective optimization evolutionary algorithm for complex environmental changes. Knowl Based Syst 2:106612
Chen R, Li K, Yao X (2018) Dynamic multiobjectives optimization with a changing number of objectives. IEEE Trans Evol Comput 22(1):157–171
Nguyen T, Yang S, Branke J (2012) Evolutionary dynamic optimization: a survey of the state of the art. Swarm Evol Comput 6:1–24
Goh C, Tan K (2009) A competitivecooperative coevolutionary paradigm for dynamic multiobjective optimization. IEEE Trans Evol Comput 13(1):103–127
Ma X, Yang J, Sun H, Hu Z, Wei L (2021) Feature information prediction algorithm for dynamic multiobjective optimization problems. Eur J Oper Res 295:965–981
Jiang S, Yang S (2017) A steadystate and generational evolutionary algorithm for dynamic multiobjective optimization. IEEE Trans Evol Comput 21(1):65–82
Zhang Q, Yang S, Jiang S, Wang R, Li X (2019) Novel prediction strategies for dynamic multiobjective optimization. IEEE Trans Evol Comput 99:1–14
Rong M, Gong D, Pedrycz W, Wang L (2019) A multimodel prediction method for dynamic multiobjective evolutionary optimization. IEEE Trans Evol Comput 99:290–304
Helbig M, Engelbrecht A (2014) Populationbased metaheuristics for continuous boundaryconstrained dynamic multiobjective optimisation problems. Swarm Evol Comput 14:31–47
Zou J, Li Q, Yang S, Bai H, Zheng J (2017) A prediction strategy based on center points and knee points for evolutionary dynamic multiobjective optimization. Appl Soft Comput 61:806–818
Liu R, Li J, Mu C, Fan J, Mu C, Li J (2017) A coevolutionary technique based on multiswarm particle swarm optimization for dynamic multiobjective optimization. Eur J Oper Res 261(3):1028–1051
Ruan G, Yu G, Zheng J, Zou J, Yang S (2017) The effect of diversity maintenance on prediction in dynamic multiobjective optimization. Appl Soft Comput 58:631–647
Zou F, Yen GG, Tang L (2020) A kneeguided prediction approach for dynamic multiobjective optimization. Inf Sci 509(2):193–209
Huang Y, Ding Y, Hao K, Jin Y (2017) A multiobjective approach to robust optimization over time considering switching cost. Inf Sci 394:183–197
Yu X, Jin Y, Tang K, Yao X (2010) Robust optimization over time a new perspective on dynamic optimization problems. In: IEEE congress on evolutionary computation. pp 1–6
Jin Y, Tang K, Yu X, Sendhoff B, Yao X (2013) A framework for finding robust optimal solutions over time. Memet Comput 5(1):3–18
Chen M, Guo Y, Gong D, Yang Z (2017) A novel dynamic multiobjective robust evolutionary optimization method. Acta Autom Sin 43(11):2014–2032
Yazdani D, Nguyen T, Branke J (2019) Robust optimization over time by learning problem space characteristics. IEEE Trans Evol Comput 23(1):143–155
Guo Y, Yang H, Chen M, Chen J, Gong D (2019) Ensemble predictionbased dynamic robust multiobjective optimization methods. Swarm Evol Comput 48:156–171
Farina M, Deb K, Amato P (2014) Dynamic multiobjective optimization problems: test cases, approximations, and applications. IEEE Trans Evol Comput 8(5):425–442
Zhou A, Jin Y, Zhang Q (2013) A population prediction strategy for evolutionary dynamic multiobjective optimization. IEEE Trans Cybern 44(1):40–53
Fu H, Sendhoff B, Tang K, Yao X (2014) Robust optimization over time: problem difficulties and benchmark problems. IEEE Trans Evol Comput 19(5):731–745
Gan R, Zheng J, Zou J, Ma Z, Yang S (2021) A random benchmark suite and a new reaction strategy in dynamic multiobjective optimization. Swarm Evol Comput 63:100867
Heng HJ, Yan XD, Wang F, Li H (2017) Research on dynamic scheduling of airport fuel filling vehicles. Comput Eng Des 38(5):1382–1388
Liu R, Li J, Jin Y, Jiao L (2021) A selfadaptive response strategy for dynamic multiobjective evolutionary optimization based on objective space decomposition. Evol Comput 29(4):491–519
Jiang M, Wang Z, Qiu L, Guo S, Gao X, Tan K (2021) A fast dynamic evolutionary multiobjective algorithm via manifold transfer learning. IEEE Trans Cybern 51(7):3417–3428
Greeff M, Engelbrecht AP (2010) Dynamic multiobjective optimisation using PSO. Stud Comput Intell 261:105–123
Guo Y, Zhang X, Gong D, Zhang Z, Yang J (2019) Novel interactive preferencebased multiobjective evolutionary optimization for bolt supporting networks. IEEE Trans Evol Comput 99:1–14
Guo Y, Zhang P, Cheng J, Wang C, Gong D (2016) Interval multiobjective quantuminspired cultural algorithms. Neural Comput Appl 30:1–14
Jia L, Zeng S, Zhou D, Zhou A, Li Z, Jing H (2011) Dynamic multiobjective differential evolution for solving constrained optimization problem. In: 2011 IEEE congress of evolutionary computation (CEC). pp 2649–2654
Helbig M, Engelbrecht AP (2013) Dynamic multiobjective optimization using PSO. Stud Comput Intell 433:147–188
He S (2003) Applied time series analysis. Peking University Press, Peking
Huang Y, Jin Y, Hao K (2020) Decisionmaking and multiobjectivization for cost sensitive robust optimization over time. Knowl Based Syst 199(8):1–14
Yazdani D, Nguyen T, Branke J, Wang J (2018) A multiobjective timelinkage approach for dynamic optimization problems with previoussolution displacement restriction. In: Proceedings of international conference on the applications of evolutionary computation. pp 864–878
Yazdani D, Branke J, Omidvar M, Nguyen T, Yao X (2018) Changing or keeping solutions in dynamic optimization problems with switching costs. In: Proceedings of the 2018 genetic and evolutionary computation conference. pp 1095–1102
Zhang Q, Li H (2007) MOEA/D: A multiobjective evolutionary algorithm based on decomposition. IEEE Trans Evol Comput 11(6):712–731
Chen H, Peter T, Yao X (2009) Probabilistic classification vector machines. IEEE Trans Neural Netw 20(6):901–914
Chen H, Peter T, Ali R, Yao X (2014) Learning in the model space for cognitive fault diagnosis. IEEE Trans Neural Netw Learn Syst 25(1):124–136
Author information
Authors and Affiliations
Corresponding authors
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Manuscript received May 12, 2022.
This work is supported by National Natural Science Foundation of China under Grant 61973305, 52121003, 61573361; Permanent (Xuzhou) Intelligent Technology Co., Ltd under Grant 2021360001; Six Talent Peak Project in Jiangsu Province under Grant 2017 DZXX046; 111 Project under Grant B21014. Also, thanks for the support of Royal Society International Exchanges 2020 Cost Share.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
About this article
Cite this article
Chen, M., Guo, Y., Jin, Y. et al. An environmentdriven hybrid evolutionary algorithm for dynamic multiobjective optimization problems. Complex Intell. Syst. 9, 659–675 (2023). https://doi.org/10.1007/s40747022008244
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s40747022008244
Keywords
 Changing environment
 Tracking moving optimum
 Robust Paretooptima over time
 Dynamic multiobjective optimization