含大規(guī)模風電的多源區(qū)域電網(wǎng)優(yōu)化調(diào)度研究
發(fā)布時間：2018-11-07 18:03
【摘要】：化石能源發(fā)電所引起的環(huán)境污染問題已經(jīng)成為制約國家能源可持續(xù)發(fā)展戰(zhàn)略的一大障礙,利用無污染、可再生的新能源代替化石能源發(fā)電,是未來電力發(fā)展趨勢之一。風電作為新能源發(fā)電中的一種,具有清潔、儲存量大和易于開發(fā)等優(yōu)點,被廣泛開發(fā)和利用。由于風電的隨機不確定性,大規(guī)模風電的接入,給電力系統(tǒng)穩(wěn)定運行帶來了一定的挑戰(zhàn)。因此,研究含大規(guī)模風電接入的電力系統(tǒng)動態(tài)特性和風功率預測以及多源區(qū)域電網(wǎng)的優(yōu)化調(diào)度,對提高風電的開發(fā)利用具有重要意義。本文對含大規(guī)模風電接入的多源區(qū)域電網(wǎng)優(yōu)化調(diào)度問題,展開了如下研究:(1)構建了含風力發(fā)電機組、水力發(fā)電機組和汽輪發(fā)電機組的多源混合電力系統(tǒng)模型,在風速波動條件下,對該系統(tǒng)模型進行了仿真分析。仿真結(jié)果表明,所建的多源混合電力系統(tǒng)的穩(wěn)定性受風電機組輸出功率波動性的影響,并能夠準確描述該電力系統(tǒng)主要參數(shù)的動態(tài)特性,為進一步研究含大規(guī)模風電接入的多源區(qū)域電網(wǎng)優(yōu)化調(diào)度研究提供支撐。(2)提出了基于粒子群神經(jīng)網(wǎng)絡(Particle Swarm Optimization and Back-propagation Neural Network,PSO-BP)的風電功率預測方法,該方法利用粒子群算法的全局搜索能力來獲得BP(Back-propagation,BP)神經(jīng)網(wǎng)絡的初始權值和閾值,很好地解決了常規(guī)BP算法收斂速度慢、易陷入局部極小等問題,并對PSO-BP算法和BP神經(jīng)網(wǎng)絡算法的預測結(jié)果進行了對比分析。根據(jù)實例預測結(jié)果表明,PSO-BP算法較BP神經(jīng)網(wǎng)絡算法預測的絕對平均誤差(Mean Absolute Error,MAE)和均方根誤差(Root Mean Square Error,RMSE)分別減少了7.02%,和9.37%,證明粒子群神經(jīng)網(wǎng)絡(PSO-BP)算法在風電場輸出功率預測方面具較理想的效果。(3)基于所建立的含風電的多源混合電力系統(tǒng)模型和風電功率預測的基礎上,研究了基于多智能體粒子群算法(Multi-agent and Particle Swarm Optimization,MA-PSO)的經(jīng)濟調(diào)度方法,該算法結(jié)合了粒子群(Particle Swarm Optimization,PSO)算法全局特性和多智能體系統(tǒng)(Multi-agent System,MAS)的智能特性,有效解決了高維數(shù)、非線性、多參數(shù)耦合的經(jīng)濟調(diào)度問題;通過對MA-PSO算法與基本PSO算法優(yōu)化結(jié)果進行對比分析,MA-PSO算法求出的一天的最優(yōu)值的發(fā)電成本為3.7964×10~4$,而PSO算法所求出的最優(yōu)值的發(fā)電成本為4.1787×10~4$。MA-PSO算法所求發(fā)電成本較PSO算法節(jié)省了3.823×10~3$,即節(jié)省率高達9.14%。證明MA-PSO算法搜索性能好,收斂精度高。同時,MA-PSO算法應用于解決經(jīng)濟調(diào)度問題,能夠獲得較好的經(jīng)濟效益和環(huán)境效益。
[Abstract]:The problem of environmental pollution caused by fossil energy power generation has become a major obstacle to the national energy sustainable development strategy. The use of non-polluting renewable new energy to replace fossil energy power generation is one of the future power development trends. Wind power, as one of the new energy generation, has the advantages of clean, large storage and easy to develop, so it has been widely developed and used. Because of the random uncertainty of wind power and the connection of large-scale wind power, it brings some challenges to the stable operation of power system. Therefore, it is of great significance to study the dynamic characteristics and wind power prediction of power system with large-scale wind power access, as well as the optimal dispatching of multi-source regional power network, in order to improve the development and utilization of wind power. In this paper, the optimal dispatching problem of multi-source regional power network with large-scale wind power access is studied as follows: (1) the model of multi-source hybrid power system with wind turbine generator, hydrogenerator and turbine generator is constructed. Under the condition of wind speed fluctuation, the system model is simulated and analyzed. The simulation results show that the stability of the multi-source hybrid power system is affected by the fluctuation of the output power of the wind turbine, and the dynamic characteristics of the main parameters of the power system can be accurately described. It provides support for further research on optimal dispatching of multi-source regional power network with large-scale wind power access. (2) A wind power prediction method based on particle swarm optimization neural network (Particle Swarm Optimization and Back-propagation Neural Network,PSO-BP) is proposed. This method utilizes the global searching ability of particle swarm optimization algorithm to obtain the initial weights and thresholds of BP (Back-propagation,BP) neural network, which solves the problems of slow convergence speed and easy to fall into local minima of conventional BP algorithm. The prediction results of PSO-BP algorithm and BP neural network algorithm are compared and analyzed. The prediction results show that the absolute mean error (Mean Absolute Error,MAE) and root mean square error (Root Mean Square Error,RMSE) of the PSO-BP algorithm are 7.02 and 9.37 less than those of the BP neural network algorithm, respectively. It is proved that the particle swarm optimization neural network (PSO-BP) algorithm is effective in predicting the output power of wind farm. (3) based on the model of multi-source hybrid power system with wind power and the prediction of wind power, The economic scheduling method based on multi-agent particle swarm optimization (Multi-agent and Particle Swarm Optimization,MA-PSO) is studied. The algorithm combines the global characteristics of particle swarm optimization (Particle Swarm Optimization,PSO) algorithm and multi-agent system (Multi-agent System,). The intelligent characteristic of MAS effectively solves the economic scheduling problem with high dimension, nonlinear and multi-parameter coupling. By comparing and analyzing the optimization results of MA-PSO algorithm and basic PSO algorithm, it is found that the optimal value of MA-PSO algorithm is 3.7964 脳 10 ~ (4) 脳 10 ~ (4) / day. The optimal value of the PSO algorithm is 4.1787 脳 10~4$.MA-PSO, and the cost is 3.823 脳 10 ~ (-3) less than that of the PSO algorithm, that is, the saving rate is as high as 9.14%. It is proved that MA-PSO algorithm has good searching performance and high convergence accuracy. At the same time, the MA-PSO algorithm is applied to solve the economic scheduling problem, which can obtain better economic and environmental benefits.
【學位授予單位】：華北水利水電大學
【學位級別】：碩士
【學位授予年份】：2017
【分類號】：TP18;TM73
本文編號：2317144
[Abstract]:The problem of environmental pollution caused by fossil energy power generation has become a major obstacle to the national energy sustainable development strategy. The use of non-polluting renewable new energy to replace fossil energy power generation is one of the future power development trends. Wind power, as one of the new energy generation, has the advantages of clean, large storage and easy to develop, so it has been widely developed and used. Because of the random uncertainty of wind power and the connection of large-scale wind power, it brings some challenges to the stable operation of power system. Therefore, it is of great significance to study the dynamic characteristics and wind power prediction of power system with large-scale wind power access, as well as the optimal dispatching of multi-source regional power network, in order to improve the development and utilization of wind power. In this paper, the optimal dispatching problem of multi-source regional power network with large-scale wind power access is studied as follows: (1) the model of multi-source hybrid power system with wind turbine generator, hydrogenerator and turbine generator is constructed. Under the condition of wind speed fluctuation, the system model is simulated and analyzed. The simulation results show that the stability of the multi-source hybrid power system is affected by the fluctuation of the output power of the wind turbine, and the dynamic characteristics of the main parameters of the power system can be accurately described. It provides support for further research on optimal dispatching of multi-source regional power network with large-scale wind power access. (2) A wind power prediction method based on particle swarm optimization neural network (Particle Swarm Optimization and Back-propagation Neural Network,PSO-BP) is proposed. This method utilizes the global searching ability of particle swarm optimization algorithm to obtain the initial weights and thresholds of BP (Back-propagation,BP) neural network, which solves the problems of slow convergence speed and easy to fall into local minima of conventional BP algorithm. The prediction results of PSO-BP algorithm and BP neural network algorithm are compared and analyzed. The prediction results show that the absolute mean error (Mean Absolute Error,MAE) and root mean square error (Root Mean Square Error,RMSE) of the PSO-BP algorithm are 7.02 and 9.37 less than those of the BP neural network algorithm, respectively. It is proved that the particle swarm optimization neural network (PSO-BP) algorithm is effective in predicting the output power of wind farm. (3) based on the model of multi-source hybrid power system with wind power and the prediction of wind power, The economic scheduling method based on multi-agent particle swarm optimization (Multi-agent and Particle Swarm Optimization,MA-PSO) is studied. The algorithm combines the global characteristics of particle swarm optimization (Particle Swarm Optimization,PSO) algorithm and multi-agent system (Multi-agent System,). The intelligent characteristic of MAS effectively solves the economic scheduling problem with high dimension, nonlinear and multi-parameter coupling. By comparing and analyzing the optimization results of MA-PSO algorithm and basic PSO algorithm, it is found that the optimal value of MA-PSO algorithm is 3.7964 脳 10 ~ (4) 脳 10 ~ (4) / day. The optimal value of the PSO algorithm is 4.1787 脳 10~4$.MA-PSO, and the cost is 3.823 脳 10 ~ (-3) less than that of the PSO algorithm, that is, the saving rate is as high as 9.14%. It is proved that MA-PSO algorithm has good searching performance and high convergence accuracy. At the same time, the MA-PSO algorithm is applied to solve the economic scheduling problem, which can obtain better economic and environmental benefits.
【學位授予單位】：華北水利水電大學
【學位級別】：碩士
【學位授予年份】：2017
【分類號】：TP18;TM73
【參考文獻】
相關期刊論文 前10條
1 謝俊;陳凱旋;岳東;李亞平;王珂;翁盛煊;黃崇鑫;;基于多智能體系統(tǒng)一致性算法的電力系統(tǒng)分布式經(jīng)濟調(diào)度策略[J];電力自動化設備;2016年02期
2 楊明莉;劉三明;王致杰;張衛(wèi);丁國棟;;卡爾曼小波神經(jīng)網(wǎng)絡風速預測[J];電力系統(tǒng)及其自動化學報;2015年12期
3 吳杰;鄭拓;梁志超;樊雅青;;基于遺傳算法的分布式能源系統(tǒng)優(yōu)化設計[J];智能電網(wǎng);2015年04期
4 陳志寶;丁杰;周海;程序;朱想;;地基云圖結(jié)合徑向基函數(shù)人工神經(jīng)網(wǎng)絡的光伏功率超短期預測模型[J];中國電機工程學報;2015年03期
5 姚建紅;張玲玉;孫大興;;改進多智能體蟻群算法在電力系統(tǒng)無功優(yōu)化中的應用[J];化工自動化及儀表;2014年05期
6 崔微;趙君;白莉紅;;基于多智能體的混合發(fā)電機組調(diào)度問題研究[J];陜西電力;2014年04期
7 李沖;鄭源;陸云;朱大勝;宋晨光;;獨立風-光-蓄混合發(fā)電系統(tǒng)的建模與優(yōu)化[J];排灌機械工程學報;2014年01期
8 盧錦玲;苗雨陽;張成相;任惠;;基于改進多目標粒子群算法的含風電場電力系統(tǒng)優(yōu)化調(diào)度[J];電力系統(tǒng)保護與控制;2013年17期
9 張少迪;;基于PSO-BP神經(jīng)網(wǎng)絡的短期負荷預測算法[J];現(xiàn)代電子技術;2013年12期
10 薛貴挺;張焰;祝達康;;混合發(fā)電系統(tǒng)的功率控制和能量管理策略[J];華東電力;2012年10期
相關會議論文 前1條
1 張麗;徐玉琴;王增平;;基于多智能體遺傳算法的配電網(wǎng)大面積斷電供電恢復算法[A];中國高等學校電力系統(tǒng)及其自動化專業(yè)第二十四屆學術年會論文集（上冊）[C];2008年
相關博士學位論文 前2條
1 涂娟娟;PSO優(yōu)化神經(jīng)網(wǎng)絡算法的研究及其應用[D];江蘇大學;2013年
2 周瑋;含風電場的電力系統(tǒng)動態(tài)經(jīng)濟調(diào)度問題研究[D];大連理工大學;2010年
相關碩士學位論文 前3條
1 劉金華;多目標遺傳算法在企業(yè)能源規(guī)劃中的應用研究[D];廣東工業(yè)大學;2013年
2 尹航;基于遺傳算法的配電網(wǎng)絡故障恢復重構研究[D];北京交通大學;2012年
3 任艷;基于遺傳算法的能源結(jié)構多目標優(yōu)化模型的研究[D];中國石油大學;2007年
，本文編號：2317144
本文鏈接：http://www.sikaile.net/kejilunwen/zidonghuakongzhilunwen/2317144.html
最近更新
教材專著
