發(fā)布時(shí)間：2018-10-09 10:35

【摘要】：高精度的風(fēng)速預(yù)測(cè)對(duì)風(fēng)電發(fā)展具有重要意義。目前針對(duì)風(fēng)速預(yù)測(cè)研究大多集中于兩方面:第一,采用中尺度數(shù)值模式進(jìn)行風(fēng)速預(yù)報(bào),但其因計(jì)算量大具有計(jì)算時(shí)長(zhǎng)和硬件設(shè)備的局限性,并且單一中尺度模式預(yù)報(bào)效果已不能滿足當(dāng)前預(yù)測(cè)精度需求,需要進(jìn)一步引入學(xué)習(xí)模型對(duì)其預(yù)報(bào)風(fēng)速進(jìn)行訂正和預(yù)測(cè);第二,采用學(xué)習(xí)模型進(jìn)行風(fēng)速預(yù)測(cè),現(xiàn)采用的學(xué)習(xí)方法大多為淺層機(jī)器學(xué)習(xí)方法,學(xué)習(xí)能力有限,預(yù)測(cè)精度還有待進(jìn)一步提高,而深度學(xué)習(xí)模型具有更深層次的學(xué)習(xí)能力,能更好地描述目標(biāo)物體。鑒于此,為了對(duì)中尺度WRF(Weather Research and Forecast,天氣研究與預(yù)報(bào))模式進(jìn)行并行優(yōu)化和提高風(fēng)速預(yù)測(cè)準(zhǔn)確率,本文主要做了以下三個(gè)工作:(1)WRF模式風(fēng)速預(yù)報(bào)效果評(píng)估:首先采用修正海拔高度后的地形資料對(duì)WRF模式進(jìn)行風(fēng)力模擬,得出修正數(shù)據(jù)在山地等復(fù)雜地形下對(duì)WRF模式具有一定影響的結(jié)果。通過獲取的簡(jiǎn)單地形下某70m高測(cè)風(fēng)塔的實(shí)際測(cè)風(fēng)數(shù)據(jù),對(duì)WRF模式重新計(jì)算后輸出的氣壓、氣溫、風(fēng)速、風(fēng)向四個(gè)氣象要素預(yù)報(bào)結(jié)果進(jìn)行了全面檢測(cè)和分析,結(jié)果表明,WRF模式預(yù)報(bào)與實(shí)測(cè)數(shù)據(jù)具有一定的整體相關(guān)性且符合建立DBN(Deep Belief Nets,深度信念網(wǎng)絡(luò))風(fēng)速預(yù)測(cè)模型的需求。(2)WRF模式的并行優(yōu)化:分別搭建了多機(jī)多核集群和小型塔式工作站兩種并行計(jì)算平臺(tái),采用三種并行方式對(duì)WRF模式進(jìn)行模擬計(jì)算,獲得了較優(yōu)的并行效能;并利用并行效率、加速比、價(jià)格等參數(shù)分別對(duì)并行方式和計(jì)算平臺(tái)進(jìn)行對(duì)比分析,以便用戶能根據(jù)計(jì)算需要合理選擇更高效的并行方式和計(jì)算平臺(tái)。(3)構(gòu)建基于WRF的DBN風(fēng)速預(yù)測(cè)模型:為提高WRF模式風(fēng)速預(yù)報(bào)的準(zhǔn)確率,引入深度學(xué)習(xí)模型DBN,該模型具有先無(wú)監(jiān)督后有監(jiān)督學(xué)習(xí)的優(yōu)點(diǎn),通過將WRF模式風(fēng)速預(yù)報(bào)結(jié)果與實(shí)測(cè)數(shù)據(jù)作為輸入對(duì)深度信念網(wǎng)絡(luò)進(jìn)行逐層訓(xùn)練,構(gòu)建了基于WRF的DBN風(fēng)速預(yù)測(cè)模型,并進(jìn)行仿真實(shí)驗(yàn)。以上實(shí)驗(yàn)驗(yàn)證了本文對(duì)WRF模式并行優(yōu)化的有效性和適用性,以及通過相關(guān)對(duì)比實(shí)驗(yàn)證明了本文構(gòu)建的風(fēng)速預(yù)測(cè)模型具有更深層次的學(xué)習(xí)能力,獲得了更高的預(yù)測(cè)精度且更具應(yīng)用性。
[Abstract]:High precision wind speed prediction is of great significance to wind power development. At present, the researches on wind speed prediction are mainly focused on two aspects: first, the mesoscale numerical model is used for wind speed prediction, but due to the large amount of calculation, it has the limitations of long calculation time and hardware equipment. And the prediction effect of single mesoscale model can no longer meet the demand of current forecast precision, so it is necessary to further introduce learning model to revise and forecast the predicted wind speed. Secondly, the learning model is used to predict the wind speed. Most of the current learning methods are shallow machine learning, with limited learning ability, and the prediction accuracy needs to be further improved, while the depth learning model has deeper learning ability and can better describe the target object. In view of this, in order to optimize the mesoscale WRF (Weather Research and Forecast, weather research and forecast model in parallel and improve the accuracy of wind speed prediction, The main work of this paper is as follows: (1) the wind speed prediction effect of WRF model is evaluated. Firstly, the wind model of WRF is simulated with the topographic data of modified altitude. The results show that the modified data have a certain influence on the WRF model under the complex terrain such as mountainous area. Based on the actual wind data obtained from a 70 m high wind tower under a simple terrain, the forecasted results of the four meteorological elements such as air pressure, air temperature, wind speed and wind direction after recalculating the WRF model are comprehensively detected and analyzed. The results show that the prediction of WRFmodel and the measured data have a certain overall correlation and accord with the demand of establishing DBN (Deep Belief Nets, depth belief network) wind speed prediction model. (2) parallel optimization of WRF model: the multi-machine multi-core cluster and the small cluster are built respectively. Two parallel computing platforms for tower workstations, Three parallel methods are used to simulate and calculate the WRF mode, and the parallel efficiency, speedup ratio, price and other parameters are used to compare and analyze the parallel mode and the computing platform, respectively, and the parallel efficiency, speedup ratio, price and other parameters are used to compare and analyze the parallel mode and the computing platform. So that users can reasonably select a more efficient parallel mode and computing platform according to the needs of computing. (3) build the DBN wind speed prediction model based on WRF: to improve the accuracy of WRF model wind speed prediction, The depth learning model (DBN,) is introduced. The model has the advantages of unsupervised learning and supervised learning. The depth belief network is trained layer by using the wind speed prediction results of WRF model and the measured data as input. A DBN wind speed prediction model based on WRF is constructed and simulated. The above experiments verify the validity and applicability of this paper to the parallel optimization of WRF model, and prove that the wind speed prediction model constructed in this paper has deeper learning ability. Higher prediction accuracy and more application are obtained.
【學(xué)位授予單位】：新疆大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TM614

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 葉小嶺;劉波;鄧華;肖寅;;基于小波分析和PSO優(yōu)化神經(jīng)網(wǎng)絡(luò)的短期風(fēng)電功率預(yù)測(cè)[J];可再生能源;2014年10期

2 于鳳鳴;李喜倉(cāng);宋進(jìn)華;高春香;卓義;;基于中尺度模式與神經(jīng)網(wǎng)絡(luò)的風(fēng)電功率預(yù)測(cè)[J];氣象科技;2013年04期

3 祝贏;柳艷香;程興宏;宋麗莉;黃鳳新;;線性滾動(dòng)極值處理方法對(duì)數(shù)值模擬風(fēng)速的訂正研究[J];熱帶氣象學(xué)報(bào);2013年04期

4 楊茂;馬秀達(dá);溫道揚(yáng);莊明振;王文靜;;風(fēng)電功率預(yù)測(cè)研究綜述[J];電測(cè)與儀表;2013年07期

5 XIU ChunBo;GUO FuHui;;Wind speed prediction by chaotic operator network based on Kalman Filter[J];Science China(Technological Sciences);2013年05期

6 汪君;王會(huì)軍;;WRF模式對(duì)江蘇如東地區(qū)風(fēng)速預(yù)報(bào)的檢驗(yàn)分析[J];氣候與環(huán)境研究;2013年02期

7 黃鳳新;劉壽東;祝贏;柳艷香;;基于滾動(dòng)極值處理的BP神經(jīng)網(wǎng)絡(luò)方法的WRF模式預(yù)報(bào)風(fēng)速訂正[J];科學(xué)技術(shù)與工程;2013年07期

8 李俊醅;莊子波;;WRF模式在LINUX集群系統(tǒng)的并行計(jì)算與評(píng)測(cè)[J];計(jì)算機(jī)技術(shù)與發(fā)展;2012年07期

9 鄧小花;魏立新;;運(yùn)用神經(jīng)網(wǎng)絡(luò)方法對(duì)WRF數(shù)值模擬結(jié)果的初步釋用[J];海洋預(yù)報(bào);2011年06期

10 羅文;王莉娜;;風(fēng)場(chǎng)短期風(fēng)速預(yù)測(cè)研究[J];電工技術(shù)學(xué)報(bào);2011年07期

相關(guān)會(huì)議論文 前3條

1 閆炎;王廷芳;董海萍;王奇;;高時(shí)空分辨率天氣預(yù)報(bào)模式在超級(jí)計(jì)算平臺(tái)的性能測(cè)試分析[A];第32屆中國(guó)氣象學(xué)會(huì)年會(huì)S3 軍用數(shù)值天氣預(yù)報(bào)技術(shù)及應(yīng)用[C];2015年

2 萬(wàn)杰;胡清華;劉金福;蘇鵬宇;于達(dá)仁;;基于深度學(xué)習(xí)理論的短期風(fēng)速多步預(yù)測(cè)方法研究[A];智能化電站技術(shù)發(fā)展研討暨電站自動(dòng)化2013年會(huì)論文集[C];2013年

3 楊仁勇;林建興;翁小芳;王凡;李云艷;;用微機(jī)集群并行方式運(yùn)轉(zhuǎn)WRF模式[A];2006年華南地區(qū)學(xué)術(shù)交流會(huì)論文集[C];2006年

相關(guān)博士學(xué)位論文 前1條

1 靳雙龍;中尺度WRF模式在風(fēng)電功率預(yù)測(cè)中的應(yīng)用研究[D];蘭州大學(xué);2013年

相關(guān)碩士學(xué)位論文 前4條

1 肖寅;基于WRF模式的短期風(fēng)速預(yù)測(cè)及訂正方法研究[D];南京信息工程大學(xué);2016年

2 雷慶坤;風(fēng)電場(chǎng)風(fēng)速預(yù)測(cè)模型研究[D];合肥工業(yè)大學(xué);2015年

3 蘇鵬宇;考慮風(fēng)速變化模式的風(fēng)速預(yù)報(bào)方法研究[D];哈爾濱工業(yè)大學(xué);2013年

4 楊江平;基于神經(jīng)網(wǎng)絡(luò)組合預(yù)測(cè)的風(fēng)電場(chǎng)風(fēng)速及發(fā)電功率短期預(yù)測(cè)[D];重慶大學(xué);2012年

，

本文編號(hào)：2259017