【正文】
(5)),并且粒子的新位置被計算。事實上,其目的是用較少的粒子選擇一個超立方體去優(yōu)化的帕累托解的集合的密度。如在以下。事實上,其目的是選擇用較少的粒子優(yōu)化的帕累托密度超立方體前。The velocity of any particle in the d dimension can be calculated by the followingequation: where all of the parameters are the same as in Equation (3), with the exception that rep(h) is the value obtained from the nondominated archive as a leader, as described in the followings.By assuming m as the number of available solutions in a hypercube, the probability roulette wheel of Equation (6) is applied to choose a hypercube with the h index. In fact, the aim is to choose a hypercube with fewer particles to optimize the density of the Paretofront.在d維的任何粒子的速度可以通過以下計算公式: where all of the parameters are the same as in Equation (3), with the exception that rep(h) is the value obtained from the nondominated archive as a leader, as described in the followings.By assuming m as the number of available solutions in a hypercube, the probability roulette wheel of Equation (6) is applied to choose a hypercube with the h index. In fact, the aim is to choose a hypercube with fewer particles to optimize the density of the Pareto front.所有的參數(shù)是相同的在方程(3),除代表(H)從非得到價值主導的檔案作為一個領袖,如在以下。在兩個目標的二維搜索空間中產(chǎn)生的超立方體的例子功能。然后,下面的方法時,直到重復次數(shù)玩完和/或算法的最終條件得到滿足。在圖1中,一個二維搜索空間和其分裂成超立方體被顯示。第一,在創(chuàng)建初始種群,計算目標函數(shù)的值,與非主導的答案都保存在一個外部檔案。在這篇文章中,使用由科埃略科埃略和拉蒙特( 2004)提出的方法 因為它具有更小的計算復雜度和更快的收斂(雷耶斯 Sierra和科埃略科埃略2006) 。 Fan等。這是第二類別的主要挑戰(zhàn)。第二類包括為每個粒子評價所有的目標函數(shù),并基于帕累托最優(yōu)概念的方法,產(chǎn)生非支配最佳位置(通常被稱為領導者)來指導的顆粒。在這些方法中,每個粒子每次只有一個目標函數(shù)進行評價,最好的位置是按照單一目標標準確定PSO規(guī)則,使用相應的目標函數(shù)。 Fan et ). In this article, a method proposed by Coello Coello and Lamont (2004) was used because it has less putational plexity and a quicker convergence (ReyesSierra and Coello Coello 2006). The following is a brief explanation of the method.First, an initial population is created, the values of the objective functions are calculated, and nondominant answers are preserved in an external archive. In the archive of nondominant answers, some hypercubes (with the same dimension as objective functions) are created. In Figure 1, an example of a twodimensional search space and its division into hypercubes is shown. In the twodimensional search space, the hypercubes are squares. Then, the following process is employed until the number of repetitions es to an end and/or the final condition of the algorithm is met. MOPSO算法MOPSO算法可以分為兩大類(雷耶斯 Sierra和科埃略科埃略2006年)。c1和c2值較小時允許每個粒子探索地點遠離已經(jīng)發(fā)現(xiàn)的好點,這些參數(shù)的值越高鼓勵粒子搜索靠攏前期點比較密集的區(qū)域(二零零六年克萊爾奇)。這些說明中,粒子的方程的在d的任何一個維度上移動是(此向量的第d部分會與D指數(shù)一起顯示)為(Parsopoulos和Vrahatis2010):其中和為在第d維度上之前的速度和粒子的位置,和是在同樣維度上的新的粒子速度和粒子的位置,此外,w為慣性重量(通常為2),r1和r2是在[0,1]范圍內(nèi)均勻地產(chǎn)生的隨機數(shù),并且提供群的隨機性飛行;C1和C2是加權因子,也分別稱為認知參數(shù)和社會參數(shù)(Shi和埃伯哈特1998年,波利等人,2007)。如果搜索空間的維數(shù)為d,在時間t的粒子的當前位置和速度是向量X,V表示。所有的粒子移動時下一次迭代發(fā)生。換句話說,每個粒子的位置是一個解決問題的辦法,它可以被目標函數(shù)評估。 and c1 and c2 are weighting factors, also called the cognitive and social parameters, respectively (Shi and Eberhart 1998, Poli et al. 2007). The weight coefficients c1 and c2 control the relative effect of the Pbest and Gbest locations on the velocity of a particle. Although lower values for c1 and c2 allow each particle to explore locations far away from already uncovered good points, higher values of these parameters encourage more intensive search of regions close to previous points (Clerc 2006). 粒子群優(yōu)化算法PSO算法是由甘乃迪和Eberhart開發(fā)的(1995),作為一種基于人工智能的優(yōu)化方法。 and are the new velocity and location of the particle in the same dimension, respectively。取而代之的是一個承諾,在眾多可行的解決方案中的一些能在合理時間內(nèi)被發(fā)現(xiàn)近優(yōu)解,(科埃略科埃略和2004年拉蒙特)。 ,M}(2)在多目標優(yōu)化的,當目標函數(shù)是復雜的和/或搜索空間是廣泛的,基于AI的方法被經(jīng)常使用。 。 。..FM是一個問題的目標函數(shù),然后xi 可以是一個非支配的答案,如果滿足以下條件,(科埃略科埃略和2004年Lomont,Sivanandam和2008年和Deepa):?答案xi不應該比所有的目標的xj更糟,換句話說,fk (xi) ≥ fk(xj) for all k ∈ {1, 2, . . . ,m} (1)對于所有的k∈{1,2。2002,Coello Coello等人。 in other words,fk (xi) ≥ fk(xj)for all k ∈ {1, 2, . . . ,m} (1)? The answer to xi is better than xj, in at least one objective, that is,fk (xi) fk(xj)for at least one k ∈ {1, 2, . . . ,m} (2)In multiobjective optimization, when the objective functions are plex and/or the search space is extensive, AIbased methods are often used. Using these methods, the entire search space is not investigated. Therefore, there is no guarantee that the definitely optimum solution can be found. Instead, there is a promise that some solutions near enough to the optimum can be found in reasonable time, regardless of the numerous feasible solutions(Coello Coello and Lamont 2004). 多目標優(yōu)化多目標優(yōu)化問題的目的是同時優(yōu)化幾個目標函數(shù)(希利爾和利伯曼1995;該和拉蒙特1999)。 Veldhuizen and Lamont 1999). Thus,there is not only one answer to a problem。該模型提出了一些基于決策者指定的參數(shù)土地整理決策。在一般情況下,PSO算法主要的優(yōu)點是其運營的靈活性和簡單性(公司2006,Van den伯格和公司2006)。最好39。PSO和GA方法的主要區(qū)別是, 假如不需要遺傳操作如交叉和變異,PSO通常很難完成。這表明許多目標必須同時考慮,具有廣闊的搜索空間(多土地用途可能的安排) 。相反,在上述研究中,土地利用布局的主要目標(相容性,依賴性,適宜性,和壓實度)被認為是在一起的。 ( 2011 )使用的非支配排序遺傳算法( NSGAII )提出了優(yōu)化土地利用三目標函數(shù)最小化的情景:轉(zhuǎn)換成本,最大化可達性,最大限度地土地使用兼容性。 ( 2008)集中在城市空間的有效利用,通過加密開發(fā),相鄰土地用途的兼容性,且正當?shù)闹亟?。在這一倡議算法,優(yōu)化過程中不同時進行;相反,它是一步一步的任何目標函數(shù),得到最好的結(jié)果用于隨后采取的下一個函數(shù)的優(yōu)化。目標函數(shù)是最大化用于開發(fā)的土地的適宜性和最大化相鄰區(qū)的兼容性。土地利用優(yōu)化的許多研究都使用了Pareto前沿。2007。帕累托解的集合是德布等的描述。( 2002)和科埃略科埃略等人。 instead, it was applied step by step for any of the objective functions, and the best results were then taken for optimization of the next function. LigmannZielinska et al. (2008) focused on the efficient utilization of urban space through infill development,patibility of adjacent land uses, and defensible redevelopment. Cao et al. (2011) used NonDominated Sorting Genetic Algorithm (NSGAII) to propose optimal landuse scenarios with three objective functions: minimizing conversion costs, maximizing accessibility, and maximizing patibilities between land uses.在其他一些研究中,目標是專注于Pareto前沿在多目標模式下同時優(yōu)化。 2002年)。此外,決策者希望探索一套替代解決方案,權衡不同的目標并做出相應的決策。這些方法的主要問題是,結(jié)果強烈地依賴于考慮到目標或功能用于結(jié)合成一個目標的權重。 ( 2011)采用粒子群優(yōu)化算法(PSO)優(yōu)化劃撥土地使用,考慮最大土地適宜性和最小改變土地形狀的成本。其他一些模型是基于人工智能(AI )方法。在一個單一的目標模式搜索解空間,一些研究人員采用經(jīng)典的優(yōu)化方法如線性規(guī)劃(LP)。Handling many objectives together is usually more plex than handling a single objective. Therefore,