發(fā)布時(shí)間：2019-04-12 11:42

【摘要】：伴隨我國(guó)新型城鎮(zhèn)化建設(shè),在增加用電需求的同時(shí)為分布式能源接入創(chuàng)造了環(huán)境。通過(guò)用戶側(cè)微電網(wǎng)進(jìn)行分布式光伏集成應(yīng)用,是實(shí)現(xiàn)新能源就地消納,降低碳排放與環(huán)境污染的重要途徑。國(guó)家相關(guān)政策已對(duì)分布式光伏未來(lái)一段時(shí)間的快速發(fā)展進(jìn)行了相關(guān)規(guī)劃,國(guó)家電網(wǎng)公司也出臺(tái)政策為分布式光伏接入提供便利條件與相關(guān)技術(shù)支持。分布式光伏接入用戶側(cè)微電網(wǎng)后,為保證微電網(wǎng)與配電網(wǎng)的穩(wěn)定與經(jīng)濟(jì)運(yùn)行,相關(guān)微電網(wǎng)負(fù)荷預(yù)測(cè)技術(shù)與分布式光伏功率預(yù)測(cè)技術(shù)需要結(jié)合用戶側(cè)微電網(wǎng)的應(yīng)用特點(diǎn)進(jìn)行深入研究。 提出采用核函數(shù)極限學(xué)習(xí)機(jī)構(gòu)建功率預(yù)測(cè)模型,采用粒子群算法離線優(yōu)化預(yù)測(cè)模型相關(guān)參數(shù),對(duì)于在線功率預(yù)測(cè)系統(tǒng),在保證預(yù)測(cè)精度的同時(shí)重點(diǎn)降低預(yù)測(cè)模型復(fù)雜度,從而構(gòu)建離線參數(shù)尋優(yōu)與在線功率預(yù)測(cè)相結(jié)合的預(yù)測(cè)方法。闡述國(guó)內(nèi)外功率預(yù)測(cè)技術(shù)的發(fā)展現(xiàn)狀,同時(shí)簡(jiǎn)要論述核函數(shù)極限學(xué)習(xí)機(jī)和粒子群算法的相關(guān)理論基礎(chǔ)。 (1)考慮到微電網(wǎng)負(fù)荷波動(dòng)較大,使用分時(shí)訓(xùn)練樣本進(jìn)行參數(shù)尋優(yōu),獲得一天各待預(yù)測(cè)時(shí)刻的最優(yōu)參數(shù)。為提高負(fù)荷預(yù)測(cè)系統(tǒng)運(yùn)行效率,僅選擇同類型日期的高相關(guān)時(shí)段歷史數(shù)據(jù)進(jìn)行模型訓(xùn)練。對(duì)于平均負(fù)荷140千瓦至1300千瓦的四個(gè)不同類型的微電網(wǎng)分別進(jìn)行1個(gè)月的負(fù)荷預(yù)測(cè),周預(yù)測(cè)誤差通常小于10%,最大不超過(guò)15%。由于微電網(wǎng)負(fù)荷可能在較短時(shí)間內(nèi)出現(xiàn)較快增長(zhǎng),研究中對(duì)預(yù)測(cè)模型參數(shù)采用周期更新的方式,且在更新后能保持原有負(fù)荷預(yù)測(cè)精度。 (2)對(duì)于分布式光伏功率預(yù)測(cè),使用基于屬性權(quán)重的訓(xùn)練樣本篩選機(jī)制來(lái)降低預(yù)測(cè)模型構(gòu)建復(fù)雜度。預(yù)測(cè)方法基于低成本的氣象信息記錄值而非數(shù)值天氣預(yù)報(bào),針對(duì)幾十千瓦級(jí)的分布式光伏系統(tǒng)進(jìn)行1個(gè)月的功率預(yù)測(cè),預(yù)測(cè)誤差約16%至18%。同時(shí)可根據(jù)屬性權(quán)重值簡(jiǎn)化預(yù)測(cè)模型,在預(yù)測(cè)精度基本不變的條件下進(jìn)一步降低計(jì)算時(shí)間。此外在分布式光伏隨機(jī)覆塵或逆變器部分故障等條件下,預(yù)測(cè)模型無(wú)需人為干預(yù)或更新參數(shù),即可保持原有預(yù)測(cè)精度與效率。
[Abstract]:Along with the construction of new urbanization in China, the environment for distributed energy access is created while increasing the demand for electricity. Distributed photovoltaic integrated application through user-side microgrid is an important way to realize on-site consumption of new energy sources and reduce carbon emissions and environmental pollution. The national relevant policies have made relevant plans for the rapid development of distributed photovoltaic in the future, and the State Grid Corporation has also issued policies to provide convenience and related technical support for distributed photovoltaic access. When distributed photovoltaic is connected to the user-side microgrid, in order to ensure the stability and economic operation of the microgrid and distribution network, The related microgrid load forecasting technology and the distributed photovoltaic power forecasting technology need to combine the user side microgrid application characteristics to carry on the in-depth research. In this paper, the kernel function limit learning mechanism is used to build the power prediction model, and the particle swarm optimization algorithm is used to optimize the parameters of the prediction model offline. For the on-line power prediction system, the prediction accuracy is guaranteed and the complexity of the prediction model is reduced. Thus, a prediction method combining off-line parameter optimization with on-line power prediction is constructed. The development status of power prediction technology at home and abroad is described, and the theoretical basis of kernel function limit learning machine and particle swarm optimization is briefly discussed. The main results are as follows: (1) considering the large load fluctuation of microgrid, the optimal parameters of each time to be predicted are obtained by using time-sharing training samples to optimize the parameters. In order to improve the efficiency of load forecasting system, only the historical data of high correlation period with the same type of date are selected for the training of the model. For four different types of microgrids with an average load of 140kW to 1300 kW for one month, the weekly forecast error is usually less than 10 percent and the maximum is no more than 15 percent. Because the load of microgrid may increase rapidly in a short time, the forecasting model parameters are updated periodically in the study, and the original load forecasting accuracy can be maintained after updating. (2) for the distributed PV power prediction, the training sample selection mechanism based on attribute weight is used to reduce the complexity of the prediction model. The forecasting method is based on low-cost meteorological information records rather than numerical weather forecasts. The prediction error is about 16% to 18% for a distributed photovoltaic system with several tens of kilowatts. At the same time, the prediction model can be simplified according to the attribute weight value, and the calculation time can be further reduced under the condition that the prediction precision is basically constant. In addition, under the conditions of distributed photovoltaic random dust cover or partial inverter failure, the prediction model can maintain the accuracy and efficiency of the original prediction without human intervention or updating of parameters.
【學(xué)位授予單位】：華北電力大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2014
【分類號(hào)】：TM615

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 陳昌松;段善旭;殷進(jìn)軍;;基于神經(jīng)網(wǎng)絡(luò)的光伏陣列發(fā)電預(yù)測(cè)模型的設(shè)計(jì)[J];電工技術(shù)學(xué)報(bào);2009年09期

2 陳昌松;段善旭;蔡濤;代倩;;基于模糊識(shí)別的光伏發(fā)電短期預(yù)測(cè)系統(tǒng)[J];電工技術(shù)學(xué)報(bào);2011年07期

3 周念成;鄧浩;王強(qiáng)鋼;李春艷;;光伏與微型燃?xì)廨啓C(jī)混合微網(wǎng)能量管理研究[J];電工技術(shù)學(xué)報(bào);2012年01期

4 魯宗相;王彩霞;閔勇;周雙喜;呂金祥;王云波;;微電網(wǎng)研究綜述[J];電力系統(tǒng)自動(dòng)化;2007年19期

5 劉玲;嚴(yán)登俊;龔燈才;張紅梅;李大鵬;;基于粒子群模糊神經(jīng)網(wǎng)絡(luò)的短期電力負(fù)荷預(yù)測(cè)[J];電力系統(tǒng)及其自動(dòng)化學(xué)報(bào);2006年03期

6 王越;衛(wèi)志農(nóng);吳佳佳;;人工神經(jīng)網(wǎng)絡(luò)預(yù)測(cè)技術(shù)在微網(wǎng)運(yùn)行中的應(yīng)用[J];電力系統(tǒng)及其自動(dòng)化學(xué)報(bào);2012年02期

7 陳民鈾;朱博;徐瑞林;徐鑫;;基于混合智能技術(shù)的微電網(wǎng)剩余負(fù)荷超短期預(yù)測(cè)[J];電力自動(dòng)化設(shè)備;2012年05期

8 朱永強(qiáng);田軍;;最小二乘支持向量機(jī)在光伏功率預(yù)測(cè)中的應(yīng)用[J];電網(wǎng)技術(shù);2011年07期

9 凌捷;;后金融危機(jī)時(shí)代中國(guó)光伏產(chǎn)業(yè)發(fā)展走向及戰(zhàn)略選擇——基于美國(guó)對(duì)華光伏“雙反”調(diào)查的思考[J];改革與戰(zhàn)略;2012年06期

10 王守相;張娜;;基于灰色神經(jīng)網(wǎng)絡(luò)組合模型的光伏短期出力預(yù)測(cè)[J];電力系統(tǒng)自動(dòng)化;2012年19期

，

本文編號(hào)：2456980