本文選題：短期風電功率預測　切入點：人工魚群算法　出處：《電力系統(tǒng)保護與控制》2017年07期 　論文類型：期刊論文

【摘要】：為提高短期風電功率預測精度,提出一種基于IAFSA-BPNN的短期風電功率預測方法。該方法通過改進的人工魚群算法來優(yōu)化BP神經(jīng)網(wǎng)絡的權(quán)值和閾值,從而提高BP神經(jīng)網(wǎng)絡的收斂速度和泛化能力。利用2014年上海某風場實測數(shù)據(jù)對新算法進行檢驗。試驗結(jié)果表明,改進的人工魚群算法一定程度上克服了原算法后期搜索的盲目性較大,收斂速度減慢,搜索精度變低的缺陷。IAFSA-BPNN混合算法在預測的穩(wěn)定性和精度、收斂速度等方面優(yōu)于BPNN、AFSA-BPNN算法。IAFSA-BPNN算法不僅能提高短期風電功率預測的精度,而且改善了預測結(jié)果穩(wěn)定性。
[Abstract]:In order to improve the accuracy of short-term wind power prediction, a short-term wind power prediction method based on IAFSA-BPNN is proposed, which optimizes the weights and thresholds of BP neural network through an improved artificial fish swarm algorithm. In order to improve the convergence speed and generalization ability of BP neural network, the new algorithm is tested with wind field data measured in Shanghai on 2014. The experimental results show that, To some extent, the improved artificial fish swarm algorithm overcomes the shortcomings of the original algorithm, such as large blindness, slow convergence speed and low searching precision. IAFSA-BPNN hybrid algorithm is stable and accurate in prediction. The convergence rate is better than that of BPNN-AFSA-BPNN. IAFSA-BPNN can not only improve the accuracy of short-term wind power prediction, but also improve the stability of prediction results.
【作者單位】： 南京信息工程大學信息與控制學院;南京信息工程大學氣象災害預報預警與評估協(xié)同創(chuàng)新中心;
【基金】：國家自然科學基金項目(41675156) 江蘇省高校優(yōu)勢學科建設(shè)工程資助項目(PAPD) 江蘇省六大人才高峰項(WLW-021)共同資助~~
【分類號】：TM614;TP18
，

本文編號：1589678