發(fā)布時間：2018-05-21 19:43

  本文選題：Elman神經(jīng)網(wǎng)絡(luò) + 主成分分析法��； 參考：《蘭州交通大學(xué)》2017年碩士論文

【摘要】：風力發(fā)電具有隨機性、間歇性等特點,導(dǎo)致風電場輸出電能產(chǎn)生較大的波動,直接接入電網(wǎng),會嚴重威脅電網(wǎng)的穩(wěn)定性、連續(xù)性和可調(diào)性。尤其是酒泉等超大規(guī)模風電基地采用集中式并網(wǎng),進一步放大了風電波動性對電網(wǎng)造成的劇烈沖擊,產(chǎn)生巨大的安全隱患。因此,針對風電出力的波動性,提出研究精確的風電功率預(yù)測方法,對實現(xiàn)風場發(fā)電量的高精度預(yù)測和安全、經(jīng)濟調(diào)度具有重要的實際價值。本文根據(jù)酒泉風電基地的對風電預(yù)報的現(xiàn)實需求,以酒泉風電基地內(nèi)某風電場及周邊測風塔的實測數(shù)據(jù)為基礎(chǔ),采用新型自適應(yīng)果蠅算法優(yōu)化改進的動態(tài)Elman神經(jīng)網(wǎng)絡(luò)對風電場進行未來24h內(nèi)短期風電功率預(yù)測研究。具體工作如下:首先根據(jù)對風功率公式的分析確定本文采用的原始輸入變量,針對原始數(shù)據(jù)的采集、傳輸以及存儲的過程中導(dǎo)致的數(shù)據(jù)缺失、錯誤等問題,對數(shù)據(jù)進行完整性、合理性的檢測,并對檢測出的異常數(shù)據(jù)進行分類,并進行均值填補和非線性回歸填補。根據(jù)對當前甘肅地區(qū)各風電場誤差數(shù)據(jù)分布和誤差產(chǎn)生原因的分析,選擇合適的誤差評價指標對本文的預(yù)測效果進行合理的評價。其次,針對Elman神經(jīng)網(wǎng)絡(luò)本身的梯度下降學(xué)習(xí)算法收斂速度慢、易陷入局部最優(yōu)的劣勢,提出通過具有良好全局尋優(yōu)性能和計算性能的自適應(yīng)果蠅優(yōu)化算法(FOA)優(yōu)化Elman神經(jīng)網(wǎng)絡(luò)模型權(quán)值、閾值,建立改進的FOA-Elman神經(jīng)網(wǎng)絡(luò)模型。最后,從提高功率預(yù)測精度的角度出發(fā),考慮到影響預(yù)測精度的因素中除了模型選擇、學(xué)習(xí)算法之外,輸入數(shù)據(jù)的有效性也是至關(guān)重要的,所以采用主成分分析法(PCA)對短期風電功率預(yù)測模型的輸入特征分析處理,經(jīng)過對輸入數(shù)據(jù)的主成分分析,得到四種互不相關(guān)的主成分,使用處理完的四種主成分作為輸入變量代入改進的FOA-Elman神經(jīng)網(wǎng)絡(luò)模型,建立PCA-FOA-Elman神經(jīng)網(wǎng)絡(luò)模型通過測試數(shù)據(jù)進行預(yù)測分析。通過實驗仿真,將PCA-FOA-Elman模型與基于自適應(yīng)果蠅算法的FOA-Elman神經(jīng)網(wǎng)絡(luò)模型以及改進Elman神經(jīng)網(wǎng)絡(luò)模型的預(yù)測效果圖和預(yù)測誤差分別進行比較分析。結(jié)果顯示:在短期風電功率預(yù)測中,建立的PCA-FOA-Elman模型的預(yù)測效果相對于Elman神經(jīng)網(wǎng)絡(luò)模型平均絕對誤差降低了39.44%,均方根誤差降低了36.45%,為提高短期風電功率預(yù)測精度提供了一種新思路,對實現(xiàn)風電的可測、可控、可調(diào)具有重要意義。
[Abstract]:Wind power generation has the characteristics of randomness and intermittency, which leads to large fluctuation of wind farm output energy and direct access to power grid, which will seriously threaten the stability, continuity and tunability of power grid. In particular, Jiuquan and other super-large scale wind power bases use centralized grid-connected, which further amplifies the severe impact of wind power fluctuation on the power grid, resulting in huge safety risks. Therefore, in view of the fluctuation of wind power output, an accurate wind power prediction method is proposed, which is of great practical value to achieve high precision prediction and safety of wind power generation and economic dispatch. According to the actual demand of wind power forecast in Jiuquan wind power base, this paper bases on the measured data of a wind farm and its surrounding wind tower in Jiuquan wind power base. A new adaptive Drosophila algorithm is used to optimize and improve the dynamic Elman neural network to predict the short-term wind power of wind farm in the next 24 hours. The specific work is as follows: firstly, according to the analysis of wind power formula, the original input variables are determined, and the data integrity is carried out in the process of collecting, transmitting and storing the original data. The rationality of the detection, and the detection of abnormal data classification, and the means of filling and nonlinear regression filling. Based on the analysis of the distribution of the error data and the causes of the errors in the current wind farms in Gansu Province, a reasonable evaluation of the prediction effect of this paper is carried out by selecting the appropriate error evaluation indexes. Secondly, for the gradient descent learning algorithm of Elman neural network itself, the convergence speed is slow, and it is easy to fall into the disadvantage of local optimum. An improved Elman neural network model based on adaptive Drosophila optimization algorithm (FOAA) with good global optimization performance and computational performance is proposed to optimize the weights and thresholds of the Elman neural network model. Finally, from the point of view of improving the accuracy of power prediction, considering the factors that affect the prediction accuracy, besides model selection and learning algorithm, the validity of input data is also very important. So we use the principal component analysis (PCA) to analyze the input characteristics of the short-term wind power prediction model, and through the principal component analysis of the input data, we get four independent principal components. The four principal components are used as input variables to replace the improved FOA-Elman neural network model, and the PCA-FOA-Elman neural network model is established to predict and analyze by testing data. Through experimental simulation, the prediction effect diagram and prediction error of PCA-FOA-Elman model, FOA-Elman neural network model based on adaptive Drosophila algorithm and improved Elman neural network model are compared and analyzed respectively. The results show that in the short-term wind power prediction, Compared with the average absolute error of Elman neural network model, the prediction effect of the established PCA-FOA-Elman model is reduced by 39.44 and the root mean square error is reduced by 36.45, which provides a new way to improve the prediction accuracy of short-term wind power, and can be used to realize the measurable and controllable wind power. Adjustable is of great significance.
【學(xué)位授予單位】：蘭州交通大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TP183;TM614

【參考文獻】

相關(guān)期刊論文 前10條

1 彭小圣;熊磊;文勁宇;程時杰;鄧迪元;馮雙磊;王勃;;風電集群短期及超短期功率預(yù)測精度改進方法綜述[J];中國電機工程學(xué)報;2016年23期

2 丁國紳;鄒海;;新型改進果蠅優(yōu)化算法[J];計算機工程與應(yīng)用;2016年21期

3 艾格林;孫永輝;衛(wèi)志農(nóng);葛夕武;孫國強;吳國梁;;基于MEA-Elman神經(jīng)網(wǎng)絡(luò)的光伏發(fā)電功率短期預(yù)測[J];電網(wǎng)與清潔能源;2016年04期

4 錢政;裴巖;曹利宵;王婧怡;荊博;;風電功率預(yù)測方法綜述[J];高電壓技術(shù);2016年04期

5 曹博;白剛;李輝;;基于PCA-GA-BP神經(jīng)網(wǎng)絡(luò)的瓦斯含量預(yù)測分析[J];中國安全生產(chǎn)科學(xué)技術(shù);2015年05期

6 王麗婕;冬雷;高爽;;基于多位置NWP與主成分分析的風電功率短期預(yù)測[J];電工技術(shù)學(xué)報;2015年05期

7 楊書Oz;舒勤;何川;;改進的果蠅算法及其在PPI網(wǎng)絡(luò)中的應(yīng)用[J];計算機應(yīng)用與軟件;2014年12期

8 郭凡;丁永生;郝礦榮;任立紅;肖純材;;基于果蠅算法優(yōu)化支持向量回歸機的紡絲性能預(yù)測[J];系統(tǒng)仿真學(xué)報;2014年10期

9 俞祥榮;張社榮;王雪紅;程井;;基于果蠅-BP神經(jīng)網(wǎng)絡(luò)算法的大壩力學(xué)參數(shù)反演[J];水利水電技術(shù);2014年09期

10 韓偉;王宏華;杜煒;;基于FOA-Elman神經(jīng)網(wǎng)絡(luò)的光伏電站短期出力預(yù)測模型[J];電測與儀表;2014年12期

相關(guān)博士學(xué)位論文 前1條

1 于文新;模擬電路故障診斷神經(jīng)智能果蠅算法研究[D];湖南大學(xué);2015年

相關(guān)碩士學(xué)位論文 前2條

1 趙龍;基于NWP和改進BP神經(jīng)網(wǎng)絡(luò)的風電功率預(yù)測研究[D];北京交通大學(xué);2015年

2 孟勇;風電功率預(yù)測系統(tǒng)的研究與開發(fā)[D];天津大學(xué);2010年

，

本文編號：1920494