多策略改进蜣螂优化算法及其在光伏发电功率预测中的应用  

Multi-strategy improved dung beetle optimization algorithm and its application in photovoltaic power generation power prediction

作　　者：姜建国[1] 金方承 毕洪波[1] JIANG Jianguo;JIN Fangcheng;BI Hongbo(School of Electrical Information Engineering,Northeast Petroleum University,Daqing 163000,China)

机构地区：[1]东北石油大学电气信息工程学院,大庆163000

出　　处：《电力需求侧管理》2024年第6期101-106,共6页Power Demand Side Management

基　　金：黑龙江省自然科学基金(LH2022F005)。

摘　　要：为了提高光伏发电功率预测的精确度,利用伯努利映射、鲸鱼优化算法的螺旋更新机制和最优个体自适应t分布3种策略改进标准蜣螂优化算法。通过在8种标准测试函数上进行验证,结果表明改进后的算法在收敛速度和寻优能力方面均有显著提升。进一步地,采用改进蜣螂优化算法优化长短期记忆网络模型(IDBO-LSTM)进行光伏发电功率预测,并与其他6种模型进行对比实验。预测结果表明,相较于其他模型,IDBO-LSTM在3种不同的天气类型下都展现出来更好的预测性能。与DBOLSTM模型相比,IDBO-LSTM的平均绝对误差率分别下降了0.08%、3.51%、4.02%。In order to improve the accuracy of photovoltaic power generation power prediction,the standard dung beetle optimization algo-rithm(DBO)was improved by using three strategies:Bernoulli mapping,the spiral update mechanism of whale optimization algorithm(WOA)and the optimal individual adaptive t-distribution.Through verification on 8 standard test functions,the results show that the im-proved algorithm has significant improvements in convergence speed and optimization ability.Furthermore,the improved dung beetle opti-mization algorithm was used to optimize the long short-term memory network model(IDBO-LSTM)for photovoltaic power generation pow-er prediction,and compared with six other models.The prediction results show that IDBO-LSTM exhibits better prediction performance un-der 3 different weather types than other models.Compared with the DBO-LSTM model,the average absolute error rate(MAPE)of IDBO-LSTM decreased by 0.08%,3.51%,4.02%,respectively.

关 键 词：光伏发电 功率预测 多策略改进 蜣螂优化算法 长短期记忆网络 

分 类 号：TM615[电气工程—电力系统及自动化]