基于云計(jì)算與機(jī)器學(xué)習(xí)的短期光伏發(fā)電功率預(yù)測(cè)研究
發(fā)布時(shí)間：2018-08-15 11:28
【摘要】：隨著全球化地能源應(yīng)用變革,可再生能源在全球能源結(jié)構(gòu)中的比例迅速增大。光伏發(fā)電作為一種高效、清潔能源,正成為可再生能源發(fā)電中的新增長(zhǎng)點(diǎn)。近年來,全球光伏產(chǎn)業(yè)市場(chǎng)強(qiáng)勁增長(zhǎng),各國(guó)新增裝機(jī)容量快速提高;但光伏發(fā)電功率受太陽(yáng)輻照度、溫度、濕度等氣象因素影響較大,具有間歇性、波動(dòng)性、周期性特點(diǎn)。大規(guī)模光伏接入會(huì)拉大電網(wǎng)峰谷差距,造成調(diào)峰困難,影響電能質(zhì)量和電網(wǎng)的安全穩(wěn)定運(yùn)行。因此,結(jié)合歷史數(shù)據(jù)與未來氣象數(shù)據(jù)有效預(yù)測(cè)光伏輸出功率,幫助調(diào)度人員合理的規(guī)劃電網(wǎng)調(diào)度,管理運(yùn)行,對(duì)于電力系統(tǒng)的安全穩(wěn)定運(yùn)行具有非常重要的意義。本文選擇短期(一天)光伏發(fā)電功率預(yù)測(cè)為主要研究?jī)?nèi)容。由于影響光伏發(fā)電的因素較為復(fù)雜,利用Pearson相關(guān)系數(shù)與Spearman秩相關(guān)系數(shù)對(duì)其進(jìn)行分析,設(shè)計(jì)基于功率的相似日聚類方法。之后,為提高光伏發(fā)電功率預(yù)測(cè)的精度,針對(duì)所得到的各聚類簇,提出了一種基于自適應(yīng)煙花算法(Adaptive FireWorks Algorithm,AFWA)優(yōu)化徑向基函數(shù)神經(jīng)網(wǎng)絡(luò)(Radial Bais Function Neural Network,RBFNN)的預(yù)測(cè)模型,利用自適應(yīng)煙花算法的種群協(xié)同搜索優(yōu)勢(shì),優(yōu)化網(wǎng)絡(luò)參數(shù)進(jìn)而實(shí)現(xiàn)更加精確地光伏出力預(yù)測(cè)。同時(shí),光伏電站在長(zhǎng)期運(yùn)行后積累了大量的歷史數(shù)據(jù),隨著電站的運(yùn)行,數(shù)據(jù)量也將越來越大,單機(jī)環(huán)境下使用大量歷史數(shù)據(jù)計(jì)算耗時(shí)較長(zhǎng),影響電網(wǎng)的快速調(diào)度。本文搭建基于內(nèi)存的Spark云計(jì)算平臺(tái),并對(duì)所提算法進(jìn)行并行化改進(jìn)實(shí)現(xiàn)。在Spark平臺(tái)上運(yùn)行算法,提高計(jì)算效率。在單機(jī)和多節(jié)點(diǎn)Spark云平臺(tái)下分別與傳統(tǒng)單一RBFNN及粒子群算法(PSO)優(yōu)化RBFNN對(duì)比實(shí)驗(yàn),驗(yàn)證所提算法提高了預(yù)測(cè)精度,且算法并行化后大大縮短了計(jì)算時(shí)間。
[Abstract]:With the transformation of global energy application, the proportion of renewable energy in the global energy structure is increasing rapidly. Photovoltaic power generation, as a kind of efficient and clean energy, is becoming a new growth point in renewable energy generation. In recent years, the global photovoltaic industry market has grown strongly, and the installed capacity of various countries has been increased rapidly. However, the photovoltaic power generation power is greatly affected by meteorological factors such as solar irradiance, temperature, humidity and so on, and has the characteristics of intermittent, volatility and periodicity. Large-scale photovoltaic access will widen the gap between peak and valley of power grid, cause difficulty of peak shaving, and affect the power quality and the safe and stable operation of power grid. Therefore, combining historical data with future meteorological data to effectively predict photovoltaic output power, help dispatchers to plan power grid dispatching reasonably, management operation, for the safe and stable operation of the power system has a very important significance. In this paper, short-term (one-day) photovoltaic power prediction is chosen as the main research content. Because the factors affecting photovoltaic power generation are complex, the similar day clustering method based on power is designed by using Pearson correlation coefficient and Spearman rank correlation coefficient. Then, in order to improve the accuracy of photovoltaic power prediction, a prediction model based on adaptive fireworks algorithm (Adaptive FireWorks algorithm) is proposed to optimize the radial basis function neural network (Radial Bais Function Neural). In order to achieve more accurate photovoltaic force prediction, the network parameters are optimized by using the population cooperative search advantage of adaptive fireworks algorithm. At the same time, photovoltaic power station has accumulated a large amount of historical data after long-term operation. With the operation of the power plant, the amount of data will be more and more large, and it will take a long time to use a large number of historical data in a single machine environment, which will affect the rapid dispatch of power grid. In this paper, Spark cloud computing platform based on memory is built, and the proposed algorithm is implemented in parallel. The algorithm is run on the Spark platform to improve the computational efficiency. Compared with the traditional single RBFNN and Particle Swarm Optimization (PSO) optimization RBFNN on single and multi-node Spark cloud platform, the proposed algorithm improves the prediction accuracy and greatly reduces the computation time after parallelization.
【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】：2017
【分類號(hào)】：TM615;TP393.09;TP18
[Abstract]:With the transformation of global energy application, the proportion of renewable energy in the global energy structure is increasing rapidly. Photovoltaic power generation, as a kind of efficient and clean energy, is becoming a new growth point in renewable energy generation. In recent years, the global photovoltaic industry market has grown strongly, and the installed capacity of various countries has been increased rapidly. However, the photovoltaic power generation power is greatly affected by meteorological factors such as solar irradiance, temperature, humidity and so on, and has the characteristics of intermittent, volatility and periodicity. Large-scale photovoltaic access will widen the gap between peak and valley of power grid, cause difficulty of peak shaving, and affect the power quality and the safe and stable operation of power grid. Therefore, combining historical data with future meteorological data to effectively predict photovoltaic output power, help dispatchers to plan power grid dispatching reasonably, management operation, for the safe and stable operation of the power system has a very important significance. In this paper, short-term (one-day) photovoltaic power prediction is chosen as the main research content. Because the factors affecting photovoltaic power generation are complex, the similar day clustering method based on power is designed by using Pearson correlation coefficient and Spearman rank correlation coefficient. Then, in order to improve the accuracy of photovoltaic power prediction, a prediction model based on adaptive fireworks algorithm (Adaptive FireWorks algorithm) is proposed to optimize the radial basis function neural network (Radial Bais Function Neural). In order to achieve more accurate photovoltaic force prediction, the network parameters are optimized by using the population cooperative search advantage of adaptive fireworks algorithm. At the same time, photovoltaic power station has accumulated a large amount of historical data after long-term operation. With the operation of the power plant, the amount of data will be more and more large, and it will take a long time to use a large number of historical data in a single machine environment, which will affect the rapid dispatch of power grid. In this paper, Spark cloud computing platform based on memory is built, and the proposed algorithm is implemented in parallel. The algorithm is run on the Spark platform to improve the computational efficiency. Compared with the traditional single RBFNN and Particle Swarm Optimization (PSO) optimization RBFNN on single and multi-node Spark cloud platform, the proposed algorithm improves the prediction accuracy and greatly reduces the computation time after parallelization.
【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】：2017
【分類號(hào)】：TM615;TP393.09;TP18
【參考文獻(xiàn)】
相關(guān)期刊論文 前10條
1 劉澤q，
本文編號(hào)：2184064
本文鏈接：http://sikaile.net/kejilunwen/zidonghuakongzhilunwen/2184064.html
最近更新
教材專著
