本文選題：輸電網(wǎng)規(guī)劃 + 人工蜂群算法��； 參考：《廣西大學(xué)》2014年碩士論文

【摘要】：隨著輸電網(wǎng)規(guī)模不斷擴(kuò)大,規(guī)劃復(fù)雜性的增加,采用智能優(yōu)化算法進(jìn)行輸電網(wǎng)規(guī)劃是很有必要的。人工蜂群算法是一種新型的智能優(yōu)化算法,因其具有計(jì)算速度快、參數(shù)少、魯棒性好和易與其他算法結(jié)合等優(yōu)點(diǎn),近年來已經(jīng)在許多領(lǐng)域得到了廣泛的應(yīng)用。本文對(duì)人工蜂群算法進(jìn)行改進(jìn),并將其應(yīng)用于輸電網(wǎng)規(guī)劃中,為輸電網(wǎng)規(guī)劃研究提供了一個(gè)全新的方向和路徑。 本文針對(duì)標(biāo)準(zhǔn)人工蜂群算法存在計(jì)算精度不高、容易過早陷入局部最優(yōu)和迭代后期速度慢等缺點(diǎn),對(duì)算法進(jìn)行六點(diǎn)改進(jìn)：(1)初始化階段采用混沌初始化方法和反向?qū)W習(xí)策略生成初始蜜源位置；(2)引領(lǐng)蜂階段引入變異算子和交叉算子來更新蜜源位置,并用退火選擇策略接受新蜜源；(3)選擇階段采用錦標(biāo)賽選擇策略來計(jì)算每個(gè)蜜源被跟隨蜂選擇的概率；(4)跟隨蜂階段引入學(xué)習(xí)因子來更新蜜源位置,并用退火選擇策略接受新蜜源；(5)為了提高當(dāng)前最優(yōu)蜜源的質(zhì)量,對(duì)其進(jìn)行動(dòng)態(tài)的混沌局部搜索；(6)偵察蜂階段對(duì)停滯進(jìn)化的蜜源進(jìn)行混沌搜索。通過對(duì)三個(gè)經(jīng)典測試函數(shù)進(jìn)行測試,結(jié)果表明,改進(jìn)人工蜂群算法能有效加快收斂速度,提高搜索精度,其性能優(yōu)于標(biāo)準(zhǔn)人工蜂群算法。 建立以年新建費(fèi)用與年網(wǎng)損費(fèi)用之和最小的輸電網(wǎng)單目標(biāo)規(guī)劃模型,并以Garver-6和Garver-18節(jié)點(diǎn)系統(tǒng)為例,驗(yàn)證改進(jìn)人工蜂群算法應(yīng)用于輸電網(wǎng)規(guī)劃中的有效性。最后建立以年新建費(fèi)用最小、年網(wǎng)損費(fèi)用最小、新建輸電走廊費(fèi)用最小和剩余輸電容量費(fèi)用最小為優(yōu)化目標(biāo)的輸電網(wǎng)多目標(biāo)規(guī)劃模型,并用改進(jìn)人工蜂群算法求解,通過算例驗(yàn)證本文提出的多目標(biāo)規(guī)劃模型的正確性和有效性。
[Abstract]:With the expansion of transmission network scale and the increase of planning complexity, it is necessary to adopt intelligent optimization algorithm for transmission network planning.Artificial bee colony algorithm is a new kind of intelligent optimization algorithm. It has been widely used in many fields in recent years because of its advantages of fast computing speed, less parameters, good robustness and easy to combine with other algorithms.In this paper, artificial bee colony algorithm is improved and applied to transmission network planning, which provides a new direction and path for transmission network planning research.In this paper, we aim at the shortcomings of standard artificial bee colony algorithm, such as low precision, easy to fall into local optimum prematurely and slow speed in late iteration, etc.In the initialization phase of the algorithm, chaotic initialization method and reverse learning strategy are used to generate the initial honey source position. The mutation operator and crossover operator are introduced to update the honey source position in the honeybee phase.Using the annealing selection strategy to accept the new honeycomb 3) the tournament selection strategy was used to calculate the selection probability of each honeybee. The learning factor was introduced in the following phase to update the honey source position.In order to improve the quality of the current optimal nectar source, a dynamic chaotic local search is carried out on the honeycomb to search the stagnant nectar source in the phase of reconnaissance bee.By testing three classical test functions, the results show that the improved artificial bee colony algorithm can effectively speed up the convergence speed and improve the search accuracy, and its performance is better than the standard artificial bee colony algorithm.A single objective programming model of transmission network is established based on the minimum sum of annual new cost and annual loss cost. Taking Garver-6 and Garver-18 node system as examples, the effectiveness of the improved artificial bee colony algorithm in transmission network planning is verified.Finally, a multi-objective programming model of transmission network with minimum annual new cost, minimum annual network loss cost, minimum cost of new transmission corridor and minimum cost of residual transmission capacity is established, and solved by improved artificial bee colony algorithm.An example is given to verify the correctness and validity of the proposed multiobjective programming model.
【學(xué)位授予單位】：廣西大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2014
【分類號(hào)】：TM715

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 黃映;李揚(yáng);翁蓓蓓;馬淑萍;;考慮電網(wǎng)脆弱性的多目標(biāo)電網(wǎng)規(guī)劃[J];電力系統(tǒng)自動(dòng)化;2010年23期

2 熊文;武鵬;陳可;王強(qiáng);;區(qū)間負(fù)荷下的輸電網(wǎng)靈活規(guī)劃方法[J];電網(wǎng)技術(shù);2012年04期

3 高衛(wèi)峰;劉三陽;黃玲玲;;受啟發(fā)的人工蜂群算法在全局優(yōu)化問題中的應(yīng)用[J];電子學(xué)報(bào);2012年12期

4 李如琦;王宗耀;謝林峰;褚金勝;;種群優(yōu)化人工魚群算法在輸電網(wǎng)擴(kuò)展規(guī)劃的應(yīng)用[J];電力系統(tǒng)保護(hù)與控制;2010年23期

5 王翔;李志勇;許國藝;王艷;;基于混沌局部搜索算子的人工蜂群算法[J];計(jì)算機(jī)應(yīng)用;2012年04期

6 鄔開俊;魯懷偉;;基于協(xié)同粒子群優(yōu)化算法的輸電網(wǎng)絡(luò)擴(kuò)展規(guī)劃[J];計(jì)算機(jī)應(yīng)用研究;2011年03期

7 單梁,強(qiáng)浩,李軍,王執(zhí)銓;基于Tent映射的混沌優(yōu)化算法[J];控制與決策;2005年02期

8 熊偉麗;徐邁;徐保國;;基于差分蜂群算法的電力系統(tǒng)經(jīng)濟(jì)負(fù)荷分配[J];控制與決策;2011年12期

9 李志勇;李玲玲;王翔;王艷;;基于Memetic框架的混沌人工蜂群算法[J];計(jì)算機(jī)應(yīng)用研究;2012年11期

10 高元海;王淳;;動(dòng)態(tài)輸電網(wǎng)絡(luò)規(guī)劃的組合編碼遺傳算法[J];電力系統(tǒng)保護(hù)與控制;2013年16期

，

本文編號(hào)：1770726