需要金幣： 800 個(gè)金幣 |
資料包括：完整論文 |  |
 |
| 轉(zhuǎn)換比率：金額 X 10=金幣數(shù)量， 例100元=1000金幣 | 論文字?jǐn)?shù)：16799 |  | |
| 折扣與優(yōu)惠：團(tuán)購最低可5折優(yōu)惠 - 了解詳情 | 論文格式：Word格式(*.doc) |  |
摘要：能源問題是人類可持續(xù)發(fā)展過程中急需解決的重大問題。隨著常規(guī)能源瀕臨枯竭，可再生能源越來越受到世界各國的重視，風(fēng)能在可再生能源中占據(jù)重要的位置。風(fēng)力發(fā)電從技術(shù)的成熟性和經(jīng)濟(jì)可行性看，在可再生能源中具有良好的前景。 由于風(fēng)力發(fā)電具有波動(dòng)性、間隙性和隨機(jī)性的特點(diǎn)，大容量的風(fēng)力發(fā)電接入電網(wǎng)，對電力系統(tǒng)的安全、穩(wěn)定運(yùn)行帶來嚴(yán)峻的挑戰(zhàn)。對于風(fēng)速功率進(jìn)行預(yù)測，是解決這一問題的有效途徑。 支持向量機(jī)（SVM）是一種新型機(jī)器學(xué)習(xí)方法，由于其出色的學(xué)習(xí)性能，在近幾年來已經(jīng)成為一個(gè)十分活躍的研究領(lǐng)域。因此，在研究支持向量機(jī)和最小二乘支持向量機(jī)相關(guān)理論的基礎(chǔ)上，為了能夠讓LS-SVM能夠獲得更好的得到回歸效果，用交叉驗(yàn)證法對模型的參數(shù)進(jìn)行了優(yōu)化選擇，從而提高最小二乘支持向量機(jī)的回歸精度和泛化能力. 關(guān)鍵詞：支持向量機(jī)，風(fēng)力發(fā)電，風(fēng)速預(yù)測 ，LS-SVM，交叉驗(yàn)證
Abstract: Energy problem is major issues to be settled urgently in process of human sustainable development. With the verge of depletion of conventional energy, renewable energy is receiving increasing attention around the world. Wind energy occupies an important position in the development of renewable energy. Wind power generation has good prospects in renewable energy sources form ripe technology and feasible financial condition. Due to the features of being fluctuant, intermittent, and stochastic of wind power, interconnection of large capacity wind farms wind with the power grid will bring about impact on the safety and stability of power systems. To predict the wind speed is an effective way to solve the problem. Support vector machine(SVM), a new method developed in recent years, is an advanced research field in machine learning. Therefore, as some collected data is far cry from training data or can be classified incorrectly in feature space, weight method is recommended to the Least Square Support Vector Machine, and a method of setting weight is given. The sample data is optimized selected by set weight. Key words: Support Vector Machine, Wind Power, Wind Speed Prediction, Least Square Support Vector Machine, Cross Validate
|
